© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205651
    Prev
    Next
    INDEX
    Explanations

    AutoModelForCausalLM, AutoTokenizer

    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
     ეს
    0.44
     Fife
    0.40
    怏
    0.40
     Fi
    0.38
     Alcohol
    0.37
     embryo
    0.37
     चाहि
    0.36
     Registered
    0.36
     yo
    0.36
     લક્ષ
    0.35
    POSITIVE LOGITS
    neider
    0.39
    thymeleaf
    0.38
     пробе
    0.37
    语
    0.37
    opencamera
    0.36
    OLI
    0.36
    議
    0.36
    Singer
    0.36
    omatic
    0.35
    Weight
    0.35
    Activations Density 0.002%

    No Known Activations