© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5298
    Prev
    Next
    INDEX
    Explanations

    CSS imports and modules

    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_39_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
     রং
    0.47
     interviewer
    0.45
    ilever
    0.44
     couplings
    0.42
     entrer
    0.40
     Coupling
    0.40
    軋
    0.40
    進入
    0.39
     HONOR
    0.39
     adsorbent
    0.39
    POSITIVE LOGITS
    бой
    0.39
     sag
    0.37
    fish
    0.35
    אות
    0.35
    шек
    0.34
    Educ
    0.34
     тә
    0.34
     minimise
    0.34
    customers
    0.34
    usak
    0.34
    Activations Density 0.004%

    No Known Activations