© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134296
    Prev
    Next
    INDEX
    Explanations

    listbox item table calendar event

    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_37_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
     selects
    0.61
     pilih
    0.59
    选
    0.59
     selecion
    0.58
     выбран
    0.58
    Chosen
    0.57
     select
    0.57
     choisi
    0.57
     selection
    0.55
     chosen
    0.55
    POSITIVE LOGITS
    luent
    0.44
     coughing
    0.40
    .$;
    0.38
    cough
    0.38
     зерка
    0.37
    iesa
    0.36
    ])$.
    0.36
    ложи
    0.36
    लाम
    0.36
    PLOY
    0.35
    Activations Density 0.002%

    No Known Activations