© 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. 3320
    Prev
    Next
    INDEX
    Explanations

    legal and consent-related vocabulary

    oai_token-act-pair · gemini-2.0-flash

    consent-related terms

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

    Requires permission/consent

    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
    TypedDataSet
    -0.45
     con
    -0.40
    Large
    -0.39
     patru
    -0.37
     наоборот
    -0.36
    low
    -0.36
     y
    -0.35
     A
    -0.35
    int
    -0.34
     sostanza
    -0.33
    POSITIVE LOGITS
    ArgsConstructor
    1.02
     Efq
    0.87
    kháu
    0.87
    جوايز
    0.86
     الحره
    0.85
    Geplaatst
    0.82
    Vidite
    0.82
    celotti
    0.80
     ―――――
    0.78
     esternos
    0.77
    Activations Density 3.225%

    No Known Activations