© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49704
    Prev
    Next
    INDEX
    Explanations

    classes of people

    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_55_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
    াড়
    0.36
    өрд
    0.35
    的意思
    0.35
     предлагает
    0.34
    賜
    0.34
    ≜
    0.34
     stood
    0.33
    썻
    0.33
    กรณ์
    0.33
     Stands
    0.33
    POSITIVE LOGITS
     who
    1.31
     whom
    1.26
    who
    1.13
     quien
    1.10
    whom
    1.00
     Whom
    0.97
     Who
    0.96
    Who
    0.96
     quienes
    0.95
     quién
    0.93
    Activations Density 0.012%

    No Known Activations