© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130004
    Prev
    Next
    INDEX
    Explanations

    arrow key or direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    켜
    0.39
    רו
    0.37
     filtering
    0.37
    dct
    0.36
     filter
    0.36
     Computing
    0.35
     urea
    0.35
    チョ
    0.35
     Ending
    0.35
     נוס
    0.34
    POSITIVE LOGITS
    AAC
    0.42
    肐
    0.40
    afen
    0.39
     karakter
    0.38
    ాత్రి
    0.38
    Ellen
    0.37
    ateful
    0.37
    ógrafo
    0.36
    marginLeft
    0.36
    RBI
    0.36
    Activations Density 0.000%

    No Known Activations