© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154620
    Prev
    Next
    INDEX
    Explanations

    en

    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_60_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
    folding
    0.52
    /**',
    0.50
     लेटर
    0.50
    efois
    0.50
    harth
    0.49
    chequer
    0.49
     ብዙውን
    0.49
     plufieurs
    0.48
    ربية
    0.48
    }^{*}$,
    0.47
    POSITIVE LOGITS
     changes
    0.50
     ignored
    0.43
     at
    0.43
     schedule
    0.42
     procedures
    0.42
     discussed
    0.42
     implemented
    0.41
     transitions
    0.40
     or
    0.40
     detected
    0.40
    Activations Density 0.000%

    No Known Activations