© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9202
    Prev
    Next
    INDEX
    Explanations

    characteristics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     કરવા
    0.64
    <0x85>
    0.63
    汉
    0.61
     bat
    0.60
     Linking
    0.59
    რობ
    0.58
    olation
    0.58
    ckt
    0.57
    Ordering
    0.57
    perms
    0.57
    POSITIVE LOGITS
    денциа
    0.79
     송
    0.74
     Godfrey
    0.73
    Kenny
    0.73
     fennel
    0.71
     snare
    0.71
     Rubens
    0.71
     선물
    0.71
     Goddess
    0.70
     Acoustics
    0.70
    Activations Density 0.113%

    No Known Activations