© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219851
    Prev
    Next
    INDEX
    Explanations

    safe and ethical assistance

    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_31_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
     Chaplain
    0.37
    Xiao
    0.36
    Sure
    0.35
     gange
    0.35
     मिन
    0.35
    igenza
    0.34
    }.",
    0.34
    Zhou
    0.34
     Sure
    0.34
    ώ
    0.34
    POSITIVE LOGITS
    diendo
    0.40
     Shine
    0.37
    હે
    0.36
     resur
    0.36
    来る
    0.36
     domínio
    0.36
    questa
    0.35
     exponer
    0.35
    дать
    0.35
    تقدم
    0.35
    Activations Density 0.006%

    No Known Activations