© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23260
    Prev
    Next
    INDEX
    Explanations

    symbols

    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_56_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
    Death
    0.44
    \;
    0.42
     bounced
    0.42
     testing
    0.40
     curling
    0.40
     फाइंड
    0.40
    ಲಿಯ
    0.39
     puerta
    0.38
     ছাপা
    0.38
     rejected
    0.37
    POSITIVE LOGITS
    ^{*
    0.50
    }^{*
    0.49
    ＊＊
    0.46
     $*
    0.46
     }^{*
    0.45
    )^{*
    0.45
    䥑
    0.38
     рукой
    0.37
     Verl
    0.37
    _{*
    0.36
    Activations Density 0.077%

    No Known Activations