© 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. 7341
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "es" but also picks up similar words in other languages used in online chat snippets, like "est".

    oai_token-act-pair · gemini-2.0-flash

    determiners and adjectives

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

    is

    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
     fallu
    -0.78
    الدراسه
    -0.74
     chré
    -0.73
     voici
    -0.71
     équilibr
    -0.70
    ConstraintMaker
    -0.70
     chrétien
    -0.70
     coû
    -0.69
     resourceCulture
    -0.68
     noires
    -0.67
    POSITIVE LOGITS
     a
    0.51
     important
    0.48
     la
    0.48
     necessary
    0.46
    DoubleQuotes
    0.42
     possible
    0.42
    elder
    0.41
     de
    0.40
     el
    0.40
     parte
    0.40
    Activations Density 0.566%

    No Known Activations