© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54065
    Prev
    Next
    INDEX
    Explanations

    verify our answer

    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_30_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
     безопас
    0.37
     fiz
    0.37
    (*
    0.37
     fois
    0.36
     bebas
    0.36
    bibfnamefont
    0.36
    }^
    0.34
    温度
    0.34
     defence
    0.33
     fdata
    0.33
    POSITIVE LOGITS
     μαζί
    0.39
     ensayo
    0.36
     mung
    0.36
    সার
    0.36
     Benjamin
    0.35
    必要があります
    0.34
     Borges
    0.34
     gostaria
    0.34
     Galveston
    0.34
    試
    0.34
    Activations Density 0.009%

    No Known Activations