© 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. 7224
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as parenthesis, brackets, comments, and code constructs such as if, get, return, or add

    oai_token-act-pair · gemini-2.0-flash

    reflexive pronouns

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

    add

    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
     Projektu
    -0.48
    justifyContent
    -0.47
    hysema
    -0.47
    ()->
    -0.45
    ();
    -0.44
    ///
    -0.44
    olas
    -0.43
    ());
    -0.43
    ("");
    -0.43
    кор
    -0.43
    POSITIVE LOGITS
     itſelf
    0.93
     purpoſe
    0.88
    ſelves
    0.86
     ſtate
    0.84
     himſelf
    0.84
     myſelf
    0.82
     becauſe
    0.82
     poffible
    0.81
     themſelves
    0.81
     whoſe
    0.79
    Activations Density 1.678%

    No Known Activations