© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206351
    Prev
    Next
    INDEX
    Explanations

    `impl` keyword before definitions

    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_37_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
     conscient
    0.38
    髙
    0.38
     Conv
    0.38
    ächen
    0.37
     refe
    0.36
     decisión
    0.35
     usuário
    0.35
     uniform
    0.35
     setUser
    0.35
    ૃતિ
    0.35
    POSITIVE LOGITS
    jected
    0.39
     ဟ
    0.38
     বিস্ফোর
    0.38
    торое
    0.35
    chrotron
    0.34
    ษฐ
    0.34
    Interpol
    0.34
    Accum
    0.34
    scal
    0.33
     windmill
    0.33
    Activations Density 0.001%

    No Known Activations