© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54100
    Prev
    Next
    INDEX
    Explanations

    err

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    rami
    0.43
    ,":
    0.41
    ="../../../
    0.40
    इस्
    0.39
    odyne
    0.39
    लीवुड
    0.39
     रक
    0.38
     "-----
    0.38
    ponential
    0.38
    デア
    0.38
    POSITIVE LOGITS
     occurring
    0.50
     ocor
    0.44
     Clear
    0.43
     occuring
    0.43
     Occurrence
    0.42
     Being
    0.41
     occurs
    0.41
     ocur
    0.39
     Emerging
    0.39
     occur
    0.38
    Activations Density 0.001%

    No Known Activations