© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90856
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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_3_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
    1
    0.86
    \
    0.70
    اء
    0.68
     can
    0.66
    ase
    0.65
    اح
    0.64
    IA
    0.63
     was
    0.60
    .
    0.60
    ems
    0.59
    POSITIVE LOGITS
    তে
    0.65
    ლის
    0.61
    ）；
    0.61
     Phó
    0.58
    นั่ง
    0.55
    ið
    0.55
    యత్
    0.54
    לו
    0.54
    idegg
    0.54
    াং
    0.54
    Activations Density 0.000%

    No Known Activations