© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87827
    Prev
    Next
    INDEX
    Explanations

    * **each** (symbol, intensity, compositor, ch

    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_23_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
     লাখ
    0.48
    以外
    0.44
    较大的
    0.44
     STAR
    0.44
     промышлен
    0.43
     ల
    0.43
    StarObject
    0.42
    ｙ
    0.42
     Practitioner
    0.42
    胖
    0.42
    POSITIVE LOGITS
    für
    0.45
    \.
    0.43
    țe
    0.42
    ,",
    0.42
    geschichte
    0.41
    wall
    0.41
     catalogs
    0.40
    󰡕
    0.40
     wondrous
    0.40
    <unused79>
    0.39
    Activations Density 0.000%

    No Known Activations