© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167632
    Prev
    Next
    INDEX
    Explanations

    code or technical

    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
    !”,
    1.09
    !”.
    0.95
    !",
    0.93
    ?”,
    0.90
    !!”
    0.89
    !!");
    0.89
    !");
    0.86
    !',
    0.86
    !!
    0.85
    !),
    0.85
    POSITIVE LOGITS
     nbsp
    0.37
    楝
    0.37
     displaystyle
    0.32
     willkommen
    0.32
    elten
    0.32
    <\/
    0.32
     makeStyles
    0.32
     $"{
    0.31
    秇
    0.31
    മ്പ
    0.30
    Activations Density 0.175%

    No Known Activations