© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38133
    Prev
    Next
    INDEX
    Explanations

    ball stop, drop, throw, rules

    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_3_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
     be
    0.74
     {})
    0.66
    ет
    0.65
     interesa
    0.62
     It
    0.61
    és
    0.61
    ولة
    0.61
    v
    0.61
     escribir
    0.60
    um
    0.59
    POSITIVE LOGITS
    the
    0.75
    a
    0.71
    ’
    0.68
    i
    0.64
    ection
    0.59
    0
    0.59
    ཙ
    0.59
    thed
    0.58
     کت
    0.58
    an
    0.57
    Activations Density 0.000%

    No Known Activations