© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36855
    Prev
    Next
    INDEX
    Explanations

    geometric points and positions

    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_11_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
    ましたが
    0.58
    ܠܐ
    0.55
     theaters
    0.54
    大战
    0.53
     الأصفر
    0.52
     passando
    0.50
    АР
    0.50
     Ủ
    0.49
     besten
    0.49
    扡
    0.49
    POSITIVE LOGITS
    ;
    0.59
     &
    0.58
    <strong>
    0.51
    īj
    0.49
     poss
    0.46
     Frequently
    0.46
     IMMEDI
    0.45
     *)$
    0.44
    in
    0.44
    ్యాన్ని
    0.43
    Activations Density 0.023%

    No Known Activations