© 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. 14520
    Prev
    Next
    INDEX
    Explanations

    partial words as part of a larger word.

    oai_token-act-pair · gemini-2.0-flash

    non-English tokens or specialized terms

    np_token-act-pair-logits · gpt-4o-mini
    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
     myſelf
    -0.97
     Efq
    -0.97
     Reſ
    -0.94
     Theſe
    -0.92
     Diſ
    -0.91
     ſche
    -0.90
     Inſ
    -0.89
     ſever
    -0.89
     Eſ
    -0.88
     raiſ
    -0.86
    POSITIVE LOGITS
    ٔ
    0.77
    gnition
    0.69
     calendriers
    0.65
    erapeutic
    0.64
    ностей
    0.62
    sbereich
    0.62
    oa̍t
    0.61
    glise
    0.61
    cillor
    0.60
    tagHelperRunner
    0.59
    Activations Density 2.595%

    No Known Activations