© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11127
    Prev
    Next
    INDEX
    Explanations

    phrases expressing opinions, judgements, or conclusions

    oai_token-act-pair · gemini-2.0-flash

    actual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     nahilalakip
    -0.99
    ViewFeatures
    -0.96
     Roskov
    -0.91
    CloseOperation
    -0.87
    </caption>
    -0.81
    principalColumn
    -0.80
    ")));
    -0.77
    styleType
    -0.76
    EndInit
    -0.75
    Personendaten
    -0.74
    POSITIVE LOGITS
     humanas
    0.50
    M
    0.50
     umane
    0.48
    ane
    0.46
     geçen
    0.45
     campagna
    0.44
     umani
    0.44
     umano
    0.44
     manusia
    0.43
     its
    0.43
    Activations Density 0.768%

    No Known Activations