© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167108
    Prev
    Next
    INDEX
    Explanations

    (

    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
    ин
    0.40
     документи
    0.40
     Subjects
    0.37
     Such
    0.37
    𝕠
    0.37
     Various
    0.36
    Packages
    0.36
     RCW
    0.35
     Vectors
    0.35
     Fine
    0.34
    POSITIVE LOGITS
     message
    0.68
    message
    0.59
     msg
    0.55
     ){
    0.54
     messaging
    0.51
     MESSAGE
    0.51
    Msg
    0.51
    Message
    0.50
     mesaj
    0.50
     Message
    0.49
    Activations Density 0.002%

    No Known Activations