© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12929
    Prev
    Next
    INDEX
    Explanations

    doi links

    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_40_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
    
    0.45
    neum
    0.40
    वेदन
    0.38
    anc
    0.37
    ža
    0.37
    굴
    0.36
    orts
    0.36
    PipelineState
    0.35
    ğlu
    0.35
     wang
    0.35
    POSITIVE LOGITS
     ৫৭
    0.39
     moods
    0.38
    に必要な
    0.38
    Canadian
    0.38
    filling
    0.38
    }-${
    0.37
     rapid
    0.36
     NEC
    0.36
     कंफ
    0.36
     ഇന്ത്യന്‍
    0.36
    Activations Density 0.000%

    No Known Activations