© 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. 81686
    Prev
    Next
    INDEX
    Explanations

    r

    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
    Berlin
    0.41
    app
    0.40
     Apo
    0.40
     உட்ப
    0.40
    Amy
    0.39
     ап
    0.39
     अमर
    0.39
    앱
    0.39
    <tbody>
    0.38
     Aman
    0.38
    POSITIVE LOGITS
     flexible
    0.41
     คว
    0.40
     Shum
    0.38
    unsqueeze
    0.38
     düzey
    0.38
     शाय
    0.38
     પ્લા
    0.37
    asă
    0.37
     Flexibility
    0.37
    verso
    0.37
    Activations Density 0.001%

    No Known Activations