© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88683
    Prev
    Next
    INDEX
    Explanations

    responding/instructions

    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_60_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
    How
    0.70
    Creating
    0.69
    Using
    0.67
    how
    0.65
    Making
    0.65
    What
    0.61
    Choosing
    0.58
    "
    0.58
    create
    0.57
    Selecting
    0.56
    POSITIVE LOGITS
     Boiling
    0.48
    <i>
    0.47
     Recurs
    0.46
     Philosophical
    0.46
     Pressure
    0.45
     ठीक
    0.43
     Distrib
    0.43
     Telefon
    0.43
     Pers
    0.43
     Tranqu
    0.43
    Activations Density 0.000%

    No Known Activations