© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244951
    Prev
    Next
    INDEX
    Explanations

    programming types

    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_40_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
     جلسه
    0.43
    钮
    0.42
    utenant
    0.41
    ঁচ
    0.39
    См
    0.39
     பெய
    0.38
    㕕
    0.38
    ㄾ
    0.38
    aryngeal
    0.38
     bất
    0.37
    POSITIVE LOGITS
    dinger
    0.42
     blow
    0.39
     Blow
    0.39
    க்கண
    0.38
     Blowing
    0.37
    fia
    0.36
    自有
    0.36
    يدا
    0.35
     nurturing
    0.34
     wrest
    0.34
    Activations Density 0.001%

    No Known Activations