© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5297
    Prev
    Next
    INDEX
    Explanations

    Long Island

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
     fluidized
    1.11
     peste
    0.93
    竽
    0.87
    𝘸
    0.84
    если
    0.84
     elig
    0.83
     sommige
    0.83
     endeavour
    0.83
     medzi
    0.82
    ang
    0.81
    POSITIVE LOGITS
     Yii
    0.95
     {.
    0.90
    फ
    0.89
     fois
    0.87
     kua
    0.85
    )}\
    0.84
    𝚗
    0.83
    ১
    0.82
    🗓
    0.81
    িণ
    0.81
    Activations Density 0.002%

    No Known Activations