© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10908
    Prev
    Next
    INDEX
    Explanations

    initiation and evolution

    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_40_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
    ኛ
    0.41
     patriarch
    0.40
    patri
    0.39
    ковы
    0.39
     patri
    0.37
     vyn
    0.37
     exemplifies
    0.36
    getAsJsonObject
    0.36
     timely
    0.36
     Patri
    0.35
    POSITIVE LOGITS
    acum
    0.40
    仵
    0.40
    study
    0.38
    plaf
    0.38
    होम
    0.36
    wark
    0.36
    Hom
    0.35
     যাব
    0.35
    Trimethyl
    0.35
    Seb
    0.35
    Activations Density 0.070%

    No Known Activations