© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145694
    Prev
    Next
    INDEX
    Explanations

    pelvis

    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_0_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
    ন
    1.73
    ن
    1.51
    ியை
    1.30
    н
    1.30
    ने
    1.27
    有很多
    1.22
    د
    1.20
     interdit
    1.18
    νες
    1.16
    要在
    1.16
    POSITIVE LOGITS
    8
    1.48
    x
    1.43
    로
    1.43
    6
    1.37
    7
    1.34
    f
    1.34
    ak
    1.31
    ק
    1.25
    ib
    1.21
    9
    1.19
    Activations Density 0.001%

    No Known Activations