© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6351
    Prev
    Next
    INDEX
    Explanations

    prison

    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_44_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
    ۜ
    0.37
     इस्ती
    0.37
     Retire
    0.36
    ๅ
    0.36
    äischen
    0.36
    idefinite
    0.36
    dbjc
    0.36
    AAE
    0.35
     Apica
    0.35
    
    0.35
    POSITIVE LOGITS
     minimum
    0.57
     Minimum
    0.55
     inmates
    0.55
    Minimum
    0.54
     Correction
    0.53
     inmate
    0.53
    Corre
    0.53
     penal
    0.52
     correction
    0.52
     Penal
    0.52
    Activations Density 0.021%

    No Known Activations