© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49233
    Prev
    Next
    INDEX
    Explanations

    history, culture, places

    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_55_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
     Rely
    0.40
     relied
    0.40
     relying
    0.38
    integrity
    0.38
     rely
    0.38
    \{\
    0.37
    TimeDict
    0.37
    Ķ
    0.37
    ósito
    0.36
    ransform
    0.36
    POSITIVE LOGITS
     числен
    0.42
     singularity
    0.38
     document
    0.37
     gusto
    0.37
    სი
    0.37
     illustrious
    0.37
     Genome
    0.36
     restitution
    0.36
     있지
    0.35
     denounce
    0.35
    Activations Density 0.006%

    No Known Activations