© 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-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261407
    Prev
    Next
    INDEX
    Explanations

    sprig or beginning of spróbował

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    k
    1.48
    ون
    1.34
    y
    1.31
    ke
    1.26
    de
    1.23
    ce
    1.16
    ور
    1.14
    n
    1.13
    ,
    1.13
    কে
    1.11
    POSITIVE LOGITS
    ０
    0.97
    ł
    0.91
    ambat
    0.90
     deset
    0.88
    affine
    0.87
     توز
    0.87
    žen
    0.86
     аўта
    0.85
    隠
    0.85
    foam
    0.84
    Activations Density 0.000%

    No Known Activations