© 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. 13814
    Prev
    Next
    INDEX
    Explanations

    copyright and company names

    oai_token-act-pair · gemini-2.0-flash

    capitalized proper nouns and their initials

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

    German companies/locations

    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
     дописавши
    -0.80
    +#+
    -0.77
    abestanden
    -0.75
    LookAnd
    -0.73
    oa̍t
    -0.71
     defaultstate
    -0.68
     snippetHide
    -0.67
     Мексичка
    -0.65
     незавершена
    -0.65
     <=",
    -0.65
    POSITIVE LOGITS
    V
    0.57
     V
    0.52
     e
    0.47
    v
    0.46
    carne
    0.43
    atte
    0.43
    Ver
    0.42
    ια
    0.42
    air
    0.41
    r
    0.41
    Activations Density 0.749%

    No Known Activations