© 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. 7319
    Prev
    Next
    INDEX
    Explanations

    code snippets including operators, parentheses, and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    programming language syntax and keywords

    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
     تضيفلها
    -1.16
    AndEndTag
    -0.91
    tagHelperRunner
    -0.88
    +#+#
    -0.87
    AxisAlignment
    -0.83
    存于互联网档案馆
    -0.82
     ModelExpression
    -0.82
     nakalista
    -0.78
    stateMutability
    -0.78
    RepeatedField
    -0.77
    POSITIVE LOGITS
     empty
    0.49
    empty
    0.48
     class
    0.44
     round
    0.42
     unit
    0.42
    in
    0.41
     k
    0.41
     Empty
    0.41
     in
    0.40
    用
    0.40
    Activations Density 0.381%

    No Known Activations