© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165470
    Prev
    Next
    INDEX
    Explanations

    Police Interceptor SUV

    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
    ใหม่
    0.21
    OOOO
    0.18
    G
    0.17
    AutoGen
    0.17
    HHHH
    0.17
    新款
    0.16
    sa
    0.16
    Acetyl
    0.16
     ใหม่
    0.16
    SIX
    0.15
    POSITIVE LOGITS
    ં
    0.15
    тая
    0.15
    inado
    0.14
    um
    0.14
     когда
    0.14
     она
    0.14
    cuando
    0.14
    ле
    0.14
    га
    0.14
     jefe
    0.14
    Activations Density 0.000%

    No Known Activations