© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9973
    Prev
    Next
    INDEX
    Explanations

    references to occurrences of events or items

    oai_token-act-pair · gemini-2.0-flash

    the word 'where' in different contexts

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

    say where

    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
     that
    -0.46
    IsMutable
    -0.46
    Hozzáférés
    -0.46
    FOR
    -0.45
    openzeppelin
    -0.44
    with
    -0.44
    that
    -0.42
     Who
    -0.42
    spli
    -0.41
    Hint
    -0.41
    POSITIVE LOGITS
     where
    1.04
    where
    0.87
     où
    0.84
    ReusableCell
    0.73
     donde
    0.68
     WHERE
    0.68
     hvor
    0.66
     podjela
    0.66
     esternos
    0.65
    Where
    0.64
    Activations Density 1.399%

    No Known Activations