© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119824
    Prev
    Next
    INDEX
    Explanations

    other two

    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_27_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
    ഞ്ഞ്
    0.40
     assunto
    0.39
     KN
    0.38
    йл
    0.36
    À
    0.36
     à
    0.36
     चतु
    0.36
     giorni
    0.35
     convin
    0.35
     convain
    0.35
    POSITIVE LOGITS
    rew
    0.44
    रुण
    0.38
    imsy
    0.37
    倉庫
    0.35
    塩素
    0.35
    ucia
    0.35
    poon
    0.35
    parts
    0.34
    পুণ
    0.34
    ࢮ
    0.33
    Activations Density 0.002%

    No Known Activations