© 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-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204456
    Prev
    Next
    INDEX
    Explanations

    Data or codes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     On
    0.61
     온
    0.57
    온
    0.56
    On
    0.56
    onc
    0.55
     ON
    0.52
     onc
    0.52
    ונ
    0.47
    оні
    0.46
    ON
    0.45
    POSITIVE LOGITS
    VA
    0.48
    Holland
    0.40
    lbs
    0.38
    ಥವಾ
    0.38
    porta
    0.38
    và
    0.38
    ।,
    0.37
    ն
    0.37
    va
    0.37
     Tern
    0.37
    Activations Density 0.000%

    No Known Activations