© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78214
    Prev
    Next
    INDEX
    Explanations

    conversation format

    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_53_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
     distill
    0.38
    谕
    0.37
    friends
    0.36
     IDA
    0.36
     स्पिन
    0.36
     defList
    0.35
     oneself
    0.34
     डैम
    0.34
     അന്ത
    0.34
    riched
    0.34
    POSITIVE LOGITS
    륜
    0.42
    ография
    0.39
     Ludwig
    0.37
     виконання
    0.37
     guitarra
    0.37
     olursa
    0.36
    quiera
    0.36
     Hamilton
    0.35
     follicles
    0.35
    োট
    0.35
    Activations Density 0.002%

    No Known Activations