© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165293
    Prev
    Next
    INDEX
    Explanations

    charging and discharging

    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_13_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
    Software
    0.48
    ä
    0.47
    es
    0.46
     similar
    0.45
     similares
    0.45
     können
    0.45
    아
    0.44
     thirst
    0.43
    墨
    0.43
    ieger
    0.42
    POSITIVE LOGITS
     Η
    0.48
    􀂾
    0.46
     Ο
    0.46
     కాల్
    0.45
    :'.
    0.44
    piej
    0.43
     遊ん
    0.43
     PSB
    0.42
    spiele
    0.42
     Encyclop
    0.41
    Activations Density 0.000%

    No Known Activations