© 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. 130022
    Prev
    Next
    INDEX
    Explanations

    typical before nouns

    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
     തിര
    0.33
    ucía
    0.32
     urč
    0.32
    কিছু
    0.32
    ℂ
    0.31
     Following
    0.30
     দশকের
    0.30
    〝
    0.30
     deflection
    0.30
    shifts
    0.30
    POSITIVE LOGITS
     nacionais
    0.36
     santi
    0.36
     fam
    0.32
    culaire
    0.32
     апре
    0.30
     prairie
    0.29
     nacionales
    0.29
     phal
    0.29
    Licenses
    0.29
    ᱔
    0.29
    Activations Density 0.008%

    No Known Activations