© 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. 48605
    Prev
    Next
    INDEX
    Explanations

    safe, convenient, amazing

    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
    任務
    0.38
     প্রা
    0.37
    ティング
    0.36
    வனம்
    0.36
    곶
    0.36
     mắn
    0.35
     जिन
    0.35
     ALB
    0.35
     NIS
    0.34
     अवगत
    0.34
    POSITIVE LOGITS
    欹
    0.40
    Nunca
    0.37
    非常に
    0.36
    ifera
    0.36
    Фран
    0.36
    ijdens
    0.36
     Korn
    0.35
    rini
    0.35
     전에
    0.35
    quit
    0.35
    Activations Density 0.000%

    No Known Activations