Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 229040
    Prev
    Next
    INDEX
    Explanations

    code sections

    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_57_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
    subsubsection
    0.43
    ###
    0.41
    ####
    0.39
    xxxxx
    0.38
     ###
    0.38
    #####
    0.36
    ----
    0.35
     ####
    0.34
     redundant
    0.33
    Implicit
    0.33
    POSITIVE LOGITS
     Nge
    0.40
     راستہ
    0.39
     बरा
    0.39
    сила
    0.38
    रियो
    0.37
     neodymium
    0.37
    ালো
    0.36
     ተጨማሪ
    0.36
    лага
    0.36
    शियम
    0.36
    Activations Density 0.002%

    No Known Activations