© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9392
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets, especially in German and Russian, as well as the phrase "it is."

    oai_token-act-pair · gemini-2.0-flash

    variable presence in code or language patterns

    np_token-act-pair-logits · gpt-4o-mini

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.64
    propTypes
    -0.63
     SwitchCompat
    -0.61
     PyLong
    -0.61
     useRouter
    -0.59
     FontFamily
    -0.56
     <<<<<<<<<<<<<<
    -0.56
    XmlSchema
    -0.56
    Atsauces
    -0.55
    featureID
    -0.54
    POSITIVE LOGITS
    Хьажоргаш
    0.45
    endregion
    0.44
    principalColumn
    0.43
    HideFlags
    0.42
    UnknownFieldSet
    0.42
    ajevo
    0.42
    iteter
    0.41
     sog
    0.40
    nlm
    0.39
     דו
    0.39
    Activations Density 0.797%

    No Known Activations