© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54418
    Prev
    Next
    INDEX
    Explanations

    ! after "I" or "You"

    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_30_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
    zont
    0.45
     effluent
    0.40
     travellers
    0.39
    риал
    0.38
     denominator
    0.38
     effluents
    0.38
     completions
    0.38
    !!!");
    0.38
     interventions
    0.37
     rakk
    0.37
    POSITIVE LOGITS
     yes
    0.38
     হ্যাঁ
    0.38
     Tada
    0.37
    ンダー
    0.37
     Dubois
    0.36
    それは
    0.36
     Sten
    0.36
     strconv
    0.35
     yep
    0.35
     ಪುಸ್ತಕ
    0.34
    Activations Density 0.030%

    No Known Activations