© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195780
    Prev
    Next
    INDEX
    Explanations

    ds ac

    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_9_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
     I
    0.81
     about
    0.79
     chagrin
    0.79
    ות
    0.77
     affirme
    0.76
    ی
    0.75
    ช
    0.75
    ہ
    0.74
    انی
    0.73
    中の
    0.73
    POSITIVE LOGITS
    ou
    0.94
    are
    0.93
    is
    0.92
    na
    0.86
    ت
    0.80
    st
    0.80
    Tiempo
    0.78
    me
    0.77
    ن
    0.74
    le
    0.73
    Activations Density 0.000%

    No Known Activations