© 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. 46239
    Prev
    Next
    INDEX
    Explanations

    Robert names

    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
    t
    0.70
    isas
    0.64
    <
    0.64
    ام
    0.59
    đena
    0.57
    ACT
    0.57
    کاری
    0.56
    im
    0.55
    L
    0.55
    anjutkan
    0.54
    POSITIVE LOGITS
     widen
    0.78
     ó
    0.75
     expand
    0.72
     amplify
    0.71
     río
    0.69
     injure
    0.68
     парт
    0.68
     for
    0.66
     with
    0.65
     electrón
    0.65
    Activations Density 0.001%

    No Known Activations