© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13908
    Prev
    Next
    INDEX
    Explanations

    chemical reactions (-->) followed by chemical formulas

    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_15_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
     manhã
    0.63
    N
    0.62
    i
    0.61
    hält
    0.61
    im
    0.59
    phi
    0.59
    dict
    0.57
     සහ
    0.57
    ES
    0.57
    unsqueeze
    0.57
    POSITIVE LOGITS
    ственных
    0.54
     fisherman
    0.53
    िक
    0.50
     stone
    0.49
    रोना
    0.49
     बाजार
    0.49
    ╽
    0.48
     আমর
    0.47
    uted
    0.47
     plante
    0.47
    Activations Density 0.005%

    No Known Activations