© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179865
    Prev
    Next
    INDEX
    Explanations

    det var

    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_29_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
     approach
    0.40
     world
    0.38
    ulously
    0.37
     treatment
    0.36
     Public
    0.36
    ̕
    0.36
    ખી
    0.35
    ?’
    0.35
     ability
    0.34
     actors
    0.34
    POSITIVE LOGITS
    the
    0.67
     the
    0.56
    The
    0.50
    thebetter
    0.49
     দ্যা
    0.48
    atorul
    0.47
    ザ
    0.46
    nThe
    0.44
     הה
    0.44
    ските
    0.44
    Activations Density 0.002%

    No Known Activations