© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154291
    Prev
    Next
    INDEX
    Explanations

    B-PER Answer

    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
    google
    0.47
    𝓮
    0.43
    ---+
    0.42
     திருக்கோ
    0.42
    columns
    0.41
    ające
    0.40
     ผ่าน
    0.40
    画像を
    0.40
    excluding
    0.40
     official
    0.39
    POSITIVE LOGITS
    답
    0.38
     ahi
    0.35
    AST
    0.34
    KBr
    0.34
    VM
    0.33
    dU
    0.33
    ency
    0.33
    uestos
    0.33
     duda
    0.33
    AAA
    0.33
    Activations Density 0.000%

    No Known Activations