© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11615
    Prev
    Next
    INDEX
    Explanations

    verbs which describe experiencing something, especially watching or hearing performances

    oai_token-act-pair · gemini-2.0-flash

    seen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     seen
    -1.95
    Seen
    -1.63
     Seen
    -1.63
    seen
    -1.55
     SEEN
    -1.37
     shown
    -0.94
    <bos>
    -0.93
     visto
    -0.85
     gezien
    -0.83
     feen
    -0.80
    POSITIVE LOGITS
     Wiktionnaire
    0.73
     utafitiHapana
    0.62
     disambiguazione
    0.61
     voile
    0.59
    }],
    0.58
    pausal
    0.54
    (',');
    0.50
    ystema
    0.50
    gya
    0.50
     виправивши
    0.50
    Activations Density 7.016%

    No Known Activations