© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179951
    Prev
    Next
    INDEX
    Explanations

    show that

    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_29_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
    琚
    0.38
     специальных
    0.35
    Gym
    0.35
    ..?
    0.34
    udni
    0.34
    *********/
    0.34
    啫
    0.34
     atmosfera
    0.34
    ?...
    0.34
    EXPER
    0.33
    POSITIVE LOGITS
    ürzt
    0.43
    ʇ
    0.42
    discard
    0.41
    delete
    0.41
     accret
    0.41
     similarly
    0.40
     sevgili
    0.38
     repudi
    0.37
     carcinogenic
    0.37
     inflationary
    0.37
    Activations Density 0.005%

    No Known Activations