© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130661
    Prev
    Next
    INDEX
    Explanations

    partition(

    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_25_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
    engo
    0.43
    തെന്ന്
    0.40
    Vậy
    0.39
    锷
    0.39
    enta
    0.39
    轻轻
    0.39
     ಮಕ್ಕ
    0.38
    ेच्छा
    0.38
    ச்சத்து
    0.38
     सल्ला
    0.38
    POSITIVE LOGITS
     unilateral
    0.37
     bedeut
    0.37
     /(
    0.36
     HL
    0.36
     unilaterally
    0.36
     SLR
    0.36
     solidar
    0.35
     reminiscent
    0.34
    >(
    0.34
     verstär
    0.34
    Activations Density 0.002%

    No Known Activations