© 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. 261294
    Prev
    Next
    INDEX
    Explanations

    spat

    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
    د
    1.30
    و
    1.18
    ري
    1.13
    τή
    1.13
    ل
    1.05
     in
    1.02
    д
    0.98
    л
    0.98
    لل
    0.89
    ó
    0.89
    POSITIVE LOGITS
    -
    1.30
    ,
    1.22
    ,【
    1.16
     पैदल
    1.12
    IN
    1.02
    ید
    1.02
     pessoal
    0.99
    an
    0.98
    a
    0.96
    お問い合わせ
    0.94
    Activations Density 0.000%

    No Known Activations