© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9240
    Prev
    Next
    INDEX
    Explanations

    various seemingly unrelated words

    oai_token-act-pair · gemini-2.0-flash

    Descriptive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Хьажоргаш
    -0.60
    ftagPool
    -0.57
    AndroidJUnit
    -0.54
     still
    -0.51
    LookAnd
    -0.49
    BeginContext
    -0.48
    Personendaten
    -0.48
    <bos>
    -0.47
    Personensuche
    -0.47
     regain
    -0.47
    POSITIVE LOGITS
    XmlAccessType
    0.69
    ThroughAttribute
    0.63
     forState
    0.63
    TargetException
    0.62
    nani
    0.61
    aryen
    0.59
     dépla
    0.59
    manera
    0.59
    nemia
    0.58
    GraphicsUnit
    0.58
    Activations Density 1.821%

    No Known Activations