© 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. 48482
    Prev
    Next
    INDEX
    Explanations

    cities, towns, Jericho, Moses

    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
    specificity
    0.45
     prologue
    0.38
     breakdown
    0.37
     Prolog
    0.36
    літи
    0.36
     Tariff
    0.35
    鋪
    0.35
    Flux
    0.35
    カスタム
    0.35
    featured
    0.34
    POSITIVE LOGITS
    கல்
    0.39
     Frans
    0.38
    ,(((
    0.37
    ἷ
    0.37
     Fuerza
    0.36
     fringes
    0.36
    indsight
    0.36
    eret
    0.36
    undas
    0.36
     Kend
    0.35
    Activations Density 0.020%

    No Known Activations