© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12004
    Prev
    Next
    INDEX
    Explanations

    shooting and physical actions

    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_40_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
    రో
    0.39
     ব্যবসার
    0.38
     کاروب
    0.38
     వ్యా
    0.38
     어머니
    0.37
    行的
    0.37
    ufig
    0.36
     애
    0.34
     tails
    0.34
     ব্যবসায়
    0.34
    POSITIVE LOGITS
    onin
    0.47
    pul
    0.42
    INDU
    0.41
     ইন্দু
    0.39
    emploi
    0.39
    enn
    0.38
    inden
    0.38
    ienia
    0.38
    (".",
    0.38
    oin
    0.38
    Activations Density 0.102%

    No Known Activations