© 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. 130637
    Prev
    Next
    INDEX
    Explanations

    Audiences, glistens, market, only, girl, characters

    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
    NEAPOLIS
    0.25
    <0x11>
    0.24
    直送
    0.24
     whak
    0.23
    活用
    0.23
    चुर
    0.23
     చెందిన
    0.23
     УК
    0.23
     کریں۔
    0.22
    ﺙ
    0.22
    POSITIVE LOGITS
     verdade
    0.23
     huv
    0.23
     Golds
    0.23
     exhibit
    0.23
     Exhibit
    0.22
     Sow
    0.22
     exhibits
    0.22
     lavado
    0.22
     Bott
    0.22
     charges
    0.22
    Activations Density 0.014%

    No Known Activations