© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43521
    Prev
    Next
    INDEX
    Explanations

    foot fetish, footrest, footboller

    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_3_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
     ácido
    0.88
     muchos
    0.80
    ກ
    0.79
     ﺍﻟ
    0.79
    ประสิทธิภาพ
    0.78
     przestr
    0.75
     músc
    0.75
     proveedor
    0.75
    ໃນ
    0.74
     ແລະ
    0.74
    POSITIVE LOGITS
    3
    0.75
    ان
    0.74
    1
    0.69
    f
    0.68
    nl
    0.67
    $?
    0.67
    ge
    0.66
    nat
    0.66
    lam
    0.64
    0
    0.64
    Activations Density 0.015%

    No Known Activations