© 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. 5257
    Prev
    Next
    INDEX
    Explanations

    tether or parked

    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
    д
    2.04
    d
    1.69
    saw
    1.60
     छे
    1.56
     Certainly
    1.56
    もら
    1.56
    neq
    1.55
    েনা
    1.55
    dare
    1.55
    lo
    1.54
    POSITIVE LOGITS
    𝑖
    2.07
    𝑠
    2.04
    𝒾
    2.01
     conduction
    2.01
    𝑟
    2.00
    𝑒
    1.97
    我
    1.95
     coch
    1.95
    გრამ
    1.94
     granules
    1.94
    Activations Density 0.027%

    No Known Activations