© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227847
    Prev
    Next
    INDEX
    Explanations

    directed to

    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_6_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
    ;
    1.14
     acus
    0.88
     Prism
    0.86
    ير
    0.85
    '
    0.84
    n
    0.83
     veces
    0.82
    o
    0.79
    f
    0.78
    ombies
    0.77
    POSITIVE LOGITS
    ل
    1.09
    л
    1.02
    لە
    0.82
    ۰
    0.81
    ल
    0.78
     condense
    0.77
    lerin
    0.74
    Baş
    0.74
    لل
    0.74
    一定要
    0.71
    Activations Density 0.001%

    No Known Activations