© 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. 154623
    Prev
    Next
    INDEX
    Explanations

    technology and options

    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
     น
    0.60
     other
    0.60
    Other
    0.57
    other
    0.56
     OTHER
    0.53
     കൂടുതൽ
    0.52
    更加
    0.51
    OTHER
    0.51
     ተጨማሪ
    0.51
     Other
    0.51
    POSITIVE LOGITS
     chromos
    0.39
     crayons
    0.36
     gráfico
    0.35
     fär
    0.35
    ファン
    0.34
    }(
    0.34
    })-
    0.34
     oorlog
    0.33
     wit
    0.33
    நல்ல
    0.33
    Activations Density 0.000%

    No Known Activations