© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206470
    Prev
    Next
    INDEX
    Explanations

    style or type

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    rimazole
    0.37
    umes
    0.34
     ause
    0.34
     Sexuality
    0.34
    벼
    0.33
    っていない
    0.33
    ностью
    0.33
    IOUS
    0.33
    ovost
    0.33
    faits
    0.33
    POSITIVE LOGITS
    式
    3.08
    식
    3.00
    式の
    2.59
    式的
    2.47
     式
    2.44
    식이
    2.39
    식을
    2.28
     식
    2.03
     thức
    1.98
     formula
    1.68
    Activations Density 0.005%

    No Known Activations