© 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. 5635
    Prev
    Next
    INDEX
    Explanations

    Cyrillic and acrylic

    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
    ºC
    2.11
    л
    2.09
    an
    2.08
     asignar
    1.99
    ្ន
    1.95
     oxidación
    1.92
     polyd
    1.90
    ق
    1.86
    ана
    1.85
     quedar
    1.82
    POSITIVE LOGITS
     অপরের
    2.01
    &=
    1.95
    ための
    1.94
    槃
    1.86
     steady
    1.85
     sangu
    1.83
    कम
    1.81
    घाट
    1.80
    푦
    1.79
     gotta
    1.77
    Activations Density 0.006%

    No Known Activations