© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164039
    Prev
    Next
    INDEX
    Explanations

    correspondence management

    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_13_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
     varies
    0.47
    विन
    0.46
    カード
    0.44
    𝓛
    0.43
    வல்
    0.42
    冷蔵
    0.42
    자에
    0.41
     rač
    0.41
     tissus
    0.41
     کارڈ
    0.41
    POSITIVE LOGITS
    ing
    0.42
    ars
    0.40
    c
    0.39
    )&=
    0.38
    ir
    0.38
    р
    0.38
     Vergangenheit
    0.37
    es
    0.37
    h
    0.37
    )\
    0.36
    Activations Density 0.001%

    No Known Activations