© 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. 5385
    Prev
    Next
    INDEX
    Explanations

    i'm

    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
    quela
    0.95
    on
    0.94
    ার
    0.91
    ];
    0.87
    ु
    0.81
     vezes
    0.81
    vdots
    0.80
    х
    0.79
     оказалось
    0.79
    碼
    0.78
    POSITIVE LOGITS
    त्रेयी
    1.10
     baryons
    1.05
    ekten
    1.03
     capacitive
    1.03
    Boosting
    1.00
    entlich
    0.99
     quasip
    0.99
    न
    0.98
    ea
    0.98
     functors
    0.98
    Activations Density 0.073%

    No Known Activations