© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165273
    Prev
    Next
    INDEX
    Explanations

    color of storm

    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_13_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
     rispond
    0.52
    melding
    0.46
     দেখবেন
    0.44
     spacings
    0.43
    אס
    0.42
     disrespectful
    0.42
     ધ્યાન
    0.42
    0.42
    ↣
    0.42
     grooves
    0.41
    POSITIVE LOGITS
     Kelley
    0.52
    Telemetry
    0.46
    n
    0.45
     we
    0.44
     मामला
    0.42
    н
    0.42
    ｎ
    0.42
     Optical
    0.41
    u
    0.41
     our
    0.41
    Activations Density 0.018%

    No Known Activations