© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137638
    Prev
    Next
    INDEX
    Explanations

    office cubicles and ceiling tiles

    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_12_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
     ning
    0.54
     M
    0.46
     wn
    0.46
     S
    0.46
     ür
    0.46
     rage
    0.45
     NSUTF
    0.45
    en
    0.45
     Ning
    0.45
     fr
    0.44
    POSITIVE LOGITS
    их
    0.47
    α
    0.47
    ાઇ
    0.46
    agens
    0.45
     workplaces
    0.44
    واكب
    0.44
    ДС
    0.44
    аст
    0.43
    κες
    0.43
    ATS
    0.42
    Activations Density 0.002%

    No Known Activations