© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215521
    Prev
    Next
    INDEX
    Explanations

    spaces and locations

    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_31_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
    悗
    0.33
    __':
    0.33
    izioni
    0.32
    ix
    0.31
    antiago
    0.31
    Texas
    0.31
     lavor
    0.31
    NSString
    0.31
    isf
    0.31
    Ts
    0.31
    POSITIVE LOGITS
     orientation
    0.37
     homeowner
    0.37
    嶌
    0.34
     orientations
    0.34
     Приступ
    0.33
    会長
    0.33
    өк
    0.33
     DUR
    0.33
     घेर
    0.33
    斂
    0.33
    Activations Density 0.000%

    No Known Activations