© 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. 130027
    Prev
    Next
    INDEX
    Explanations

    as far as

    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
     directamente
    0.48
     langsung
    0.45
    直接
    0.43
    يهم
    0.43
     diretamente
    0.41
    ﻊ
    0.41
    ન્દ
    0.40
     direttamente
    0.39
    eserc
    0.39
     ου
    0.38
    POSITIVE LOGITS
     Jor
    0.38
     DCT
    0.38
     reeling
    0.37
     Tetrahedron
    0.36
    rogen
    0.36
     кафед
    0.36
     Gameplay
    0.36
    職
    0.36
     recognises
    0.36
    }=\{\
    0.36
    Activations Density 0.000%

    No Known Activations