© 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. 75396
    Prev
    Next
    INDEX
    Explanations

    getting boxed in

    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
     вру
    0.40
    ჩ
    0.39
    bt
    0.38
    orgh
    0.37
     traders
    0.37
    ort
    0.36
     Trader
    0.36
    ifts
    0.35
    смотрите
    0.35
    atial
    0.35
    POSITIVE LOGITS
    륵
    0.38
    Tissue
    0.38
     새
    0.37
    ગ્ર
    0.37
    வையில்
    0.37
    GetWidth
    0.37
    விலான
    0.37
     население
    0.37
    Arist
    0.36
    യില്ല
    0.36
    Activations Density 0.000%

    No Known Activations