© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    code-related text and bracketed numbers and related wording

    oai_token-act-pair · gemini-2.0-flash

    punctuation related to ending sentences

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

    code and URLs

    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
    DoubleQuotes
    -0.53
    Бахар
    -0.49
    yntaxException
    -0.47
     actionMode
    -0.46
     She
    -0.45
    holt
    -0.43
    Ingrédients
    -0.42
    ℗
    -0.41
    vise
    -0.41
    +:+
    -0.41
    POSITIVE LOGITS
     ".
    1.42
    ".
    1.38
    '.
    1.30
     '.
    1.24
    .".
    1.16
    !".
    1.09
    ”.
    1.04
    =".
    1.03
    ?".
    1.03
    .'.
    1.00
    Activations Density 0.641%

    No Known Activations