© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198585
    Prev
    Next
    INDEX
    Explanations

    specifying concrete examples

    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_9_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
     슬
    0.58
     actuators
    0.57
    し
    0.55
    Refrigerator
    0.54
     detainees
    0.54
     تھیں۔
    0.52
     ہیں۔
    0.51
     서
    0.51
     dolphins
    0.50
    ಟ್ರ
    0.50
    POSITIVE LOGITS
     =
    0.62
     Ed
    0.47
    gement
    0.46
     [...]
    0.44
     বঙ্গ
    0.43
     Refer
    0.43
     CH
    0.43
     Mayor
    0.43
     Of
    0.42
    ,
    0.42
    Activations Density 0.000%

    No Known Activations