© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229253
    Prev
    Next
    INDEX
    Explanations

    bar

    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
     ro
    0.46
     يه
    0.44
     ex
    0.42
    rman
    0.40
     gn
    0.40
    ro
    0.39
     fe
    0.38
     납
    0.38
    roa
    0.37
    rales
    0.37
    POSITIVE LOGITS
    ণু
    0.45
    કિસ્તા
    0.43
    ണ
    0.43
    녁
    0.42
    ärts
    0.39
    បត្តិ
    0.39
     guad
    0.38
     energético
    0.38
    artney
    0.38
    ackets
    0.38
    Activations Density 0.000%

    No Known Activations