© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44456
    Prev
    Next
    INDEX
    Explanations

    smarter

    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
    ING
    0.84
    un
    0.81
    ur
    0.78
    т
    0.76
    on
    0.69
     that
    0.66
    ח
    0.65
    h
    0.63
    AM
    0.61
    tained
    0.60
    POSITIVE LOGITS
    ید
    0.73
    in
    0.59
     próprios
    0.58
     ਆਪਣ
    0.56
    ับ
    0.55
    dois
    0.55
    9
    0.55
    3
    0.55
    wijl
    0.55
    8
    0.54
    Activations Density 0.003%

    No Known Activations