© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49176
    Prev
    Next
    INDEX
    Explanations

    first followed by interest

    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_31_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
     standard
    0.34
    ましい
    0.33
    rapati
    0.32
    igable
    0.32
    龺
    0.32
    ionante
    0.32
    []>
    0.31
     vostra
    0.31
    ikannya
    0.31
    ভাবেই
    0.30
    POSITIVE LOGITS
    加盟
    0.36
    结
    0.35
     καρ
    0.35
     ;$
    0.33
    Pers
    0.33
    σκε
    0.32
     prič
    0.31
     côt
    0.30
    रासत
    0.30
     विका
    0.30
    Activations Density 0.073%

    No Known Activations