© 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. 42319
    Prev
    Next
    INDEX
    Explanations

    menu items or bar

    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
    t
    0.80
    h
    0.76
    f
    0.74
    𝟎
    0.72
     Strateg
    0.64
     on
    0.63
     obej
    0.63
     nanos
    0.62
    лся
    0.59
    hout
    0.59
    POSITIVE LOGITS
    م
    0.92
    ра
    0.78
    ିକ
    0.73
    و
    0.70
    ول
    0.69
    January
    0.69
    բ
    0.66
    ные
    0.65
    ER
    0.64
    measurement
    0.64
    Activations Density 0.000%

    No Known Activations