© 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. 166999
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     existentes
    0.42
     singleRun
    0.40
     инде
    0.39
     antrop
    0.39
    δη
    0.38
    
    0.38
     OO
    0.37
    URN
    0.36
     Rooster
    0.36
     favoritas
    0.36
    POSITIVE LOGITS
    aric
    0.43
     physically
    0.42
    arctica
    0.42
    ভূতি
    0.41
    ivated
    0.40
     shrewd
    0.40
    劾
    0.40
    ibular
    0.39
     notable
    0.39
    ic
    0.38
    Activations Density 0.000%

    No Known Activations