© 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. 5448
    Prev
    Next
    INDEX
    Explanations

    Kovitz

    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
    sion
    0.48
    at
    0.47
    ன்
    0.47
    aient
    0.46
    з
    0.45
    ge
    0.45
    noc
    0.44
    ین
    0.44
    пер
    0.44
    nier
    0.43
    POSITIVE LOGITS
     pleinement
    0.60
    CLOSED
    0.56
    ".$
    0.56
    しており
    0.55
     veryvery
    0.54
    ದ್ದರಿಂದ
    0.54
     radiated
    0.53
     する
    0.52
    arlal
    0.52
    emel
    0.52
    Activations Density 0.001%

    No Known Activations