© 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-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119400
    Prev
    Next
    INDEX
    Explanations

    from/to/by relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Drug
    0.31
    bry
    0.31
    妓
    0.31
    AllCaps
    0.31
    ⅓
    0.31
     occupying
    0.30
     అత్య
    0.30
    最高
    0.30
    Rail
    0.30
    joyed
    0.30
    POSITIVE LOGITS
     전기
    0.34
     සහ
    0.32
     및
    0.31
     radic
    0.30
     ووٹ
    0.30
    鎵
    0.30
     exponent
    0.30
     yena
    0.30
     zes
    0.29
     multitask
    0.29
    Activations Density 0.005%

    No Known Activations