© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200823
    Prev
    Next
    INDEX
    Explanations

    scores or performance

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Mario
    0.38
     holistic
    0.38
     conj
    0.37
    ésus
    0.35
     mario
    0.35
    പ്പി
    0.35
    임
    0.35
    usions
    0.35
     дви
    0.35
     avanz
    0.35
    POSITIVE LOGITS
     polyt
    0.46
     scored
    0.41
     Poly
    0.40
     Score
    0.39
    niu
    0.39
    査
    0.39
    观测
    0.38
    佾
    0.38
     scoring
    0.38
    setData
    0.38
    Activations Density 0.001%

    No Known Activations