© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146256
    Prev
    Next
    INDEX
    Explanations

    rob followed by bed, ble, or ution

    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_0_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
    ästä
    1.15
     dimes
    1.09
    स्तिष्क
    1.08
     I
    1.07
     হইয়৷
    1.04
     인해
    1.03
     and
    1.02
     molybdenum
    1.02
    är
    1.01
    りに
    1.01
    POSITIVE LOGITS
    y
    1.84
    the
    1.69
    는
    1.59
    u
    1.55
    是
    1.52
    am
    1.51
    an
    1.46
    in
    1.45
     (
    1.39
    ك
    1.36
    Activations Density 0.003%

    No Known Activations