© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68057
    Prev
    Next
    INDEX
    Explanations

    batch commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    solo
    0.38
    clap
    0.37
    력
    0.37
    Hello
    0.36
    Bal
    0.36
    égalité
    0.35
    hello
    0.35
    ării
    0.35
     pension
    0.34
    وكب
    0.34
    POSITIVE LOGITS
     ağı
    0.37
     brushes
    0.37
     antiph
    0.35
    বিএন
    0.34
    तौर
    0.34
    酮
    0.34
    agha
    0.33
     stumbling
    0.33
     Rosen
    0.32
     Gaut
    0.32
    Activations Density 0.000%

    No Known Activations