© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14465
    Prev
    Next
    INDEX
    Explanations

    words related to social identity, stereotypes and liberation

    oai_token-act-pair · gemini-2.0-flash

    Social and cultural commentary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    addCriterion
    -0.90
     endforeach
    -0.82
    Jîn
    -0.73
    featureID
    -0.70
    WithIOException
    -0.69
    glEnd
    -0.68
    styleType
    -0.67
     PyLong
    -0.66
    Portály
    -0.66
     actionMode
    -0.66
    POSITIVE LOGITS
    ฯ
    0.47
    aran
    0.44
    cos
    0.43
    佗
    0.42
     American
    0.42
    Cos
    0.42
     operate
    0.41
     sáng
    0.40
    at
    0.40
    ia
    0.39
    Activations Density 4.298%

    No Known Activations