© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204076
    Prev
    Next
    INDEX
    Explanations

    .

    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_37_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
    firetruck
    0.38
     hide
    0.37
     timeCounter
    0.37
    ≫
    0.37
    audioType
    0.36
     âng
    0.35
     pages
    0.35
     personagens
    0.35
     工
    0.34
     detach
    0.34
    POSITIVE LOGITS
    iciencia
    0.37
    vite
    0.36
    berra
    0.36
    ረው
    0.35
    गर्
    0.35
    Magic
    0.34
    Allen
    0.34
    NotIn
    0.34
    戛
    0.34
    alley
    0.34
    Activations Density 0.000%

    No Known Activations