© 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. 23538
    Prev
    Next
    INDEX
    Explanations

    banking IC

    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
     impression
    0.38
     impressions
    0.38
     Makers
    0.37
     regol
    0.37
    льність
    0.36
     modesty
    0.36
    ẻ
    0.35
     fé
    0.35
     accuracy
    0.35
    спе
    0.35
    POSITIVE LOGITS
     IC
    1.00
     axis
    0.86
     Axis
    0.85
    Axis
    0.82
    axis
    0.80
    IC
    0.79
    State
    0.73
     State
    0.72
     H
    0.69
     आईसी
    0.69
    Activations Density 0.015%

    No Known Activations