© 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. 46218
    Prev
    Next
    INDEX
    Explanations

    lexmark ms toner

    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
    ливо
    0.63
    -
    0.63
     -
    0.58
    <0xA1>
    0.57
     hình
    0.55
     dood
    0.54
    }.
    0.52
    یل
    0.52
     secondly
    0.51
    কার
    0.50
    POSITIVE LOGITS
    harap
    0.64
    ருக
    0.61
    achter
    0.60
    port
    0.59
    aja
    0.57
    be
    0.56
    PRE
    0.56
    FER
    0.56
    orsion
    0.56
    RED
    0.55
    Activations Density 0.014%

    No Known Activations