© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175171
    Prev
    Next
    INDEX
    Explanations

    which of these

    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_20_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
    t
    0.48
     Automotive
    0.45
     Motivational
    0.44
     Automobile
    0.41
     खर
    0.39
    tro
    0.38
    leur
    0.38
     Bot
    0.38
     boca
    0.38
    наче
    0.38
    POSITIVE LOGITS
    কিত
    0.49
     diesen
    0.45
    얗
    0.45
     residues
    0.45
     kardeş
    0.44
     sulfides
    0.43
    INTS
    0.43
     deftly
    0.42
     succinctly
    0.42
     heres
    0.42
    Activations Density 0.001%

    No Known Activations