© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135769
    Prev
    Next
    INDEX
    Explanations

    compare to lists, dates, speed

    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_37_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
    ಲಾಗುತ್ತದೆ
    0.39
    Params
    0.35
    Sob
    0.35
     formContext
    0.35
    Activities
    0.35
     মনোরম
    0.35
    馳
    0.35
    点评
    0.35
     স্রো
    0.34
    뿯
    0.34
    POSITIVE LOGITS
    stantially
    0.40
     நார்
    0.39
    ető
    0.38
     Sanitary
    0.38
    zle
    0.37
     tercer
    0.36
     Mujhe
    0.36
     qq
    0.36
     sanit
    0.36
    tnie
    0.35
    Activations Density 0.003%

    No Known Activations