© 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. 48419
    Prev
    Next
    INDEX
    Explanations

    final result

    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
     prepares
    0.38
     hardening
    0.34
     fatten
    0.34
     preparing
    0.34
    ច្
    0.32
     prepare
    0.32
    خة
    0.31
    칭
    0.31
     આવે
    0.30
     گذا
    0.30
    POSITIVE LOGITS
     ಸಂ
    0.41
    Hasil
    0.38
     पॉ
    0.38
     संत
    0.37
    ifilm
    0.36
    सूचित
    0.36
     connotations
    0.36
     Тогда
    0.35
    harry
    0.35
    Suzanne
    0.35
    Activations Density 0.004%

    No Known Activations