© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13117
    Prev
    Next
    INDEX
    Explanations

    a mix of accented characters, and potentially the letter E by itself

    oai_token-act-pair · gemini-2.0-flash

    ©/E

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Ссылки
    -0.47
    ByExample
    -0.46
     Photocase
    -0.45
    addGap
    -0.43
    AnchorStyles
    -0.42
     cref
    -0.42
     lenker
    -0.41
    foro
    -0.40
    matory
    -0.40
     Violence
    -0.39
    POSITIVE LOGITS
    IsMutable
    0.76
    __":
    0.74
    __':
    0.71
    __":
    0.69
    __':
    0.69
     ModelExpression
    0.65
    ysacchar
    0.60
     kasarigan
    0.59
     varandra
    0.59
     hemma
    0.58
    Activations Density 0.617%

    No Known Activations