© 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. 7586
    Prev
    Next
    INDEX
    Explanations

    code imports and system objects

    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
    dbo
    0.55
     core
    0.44
     dbo
    0.43
    utils
    0.42
     utils
    0.40
     ::
    0.39
    ኛውም
    0.38
     naï
    0.38
    springframework
    0.38
     بھارت
    0.38
    POSITIVE LOGITS
    岕
    0.36
     رحم
    0.35
    េ
    0.33
    高志森
    0.33
    ]+
    0.33
    ონ
    0.33
    धारी
    0.32
    以来
    0.32
    楡
    0.32
    imet
    0.31
    Activations Density 0.040%

    No Known Activations