© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48840
    Prev
    Next
    INDEX
    Explanations

    biblical, descriptive, verbose writing

    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_31_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
     wu
    0.36
     রাস্তায়
    0.34
     encour
    0.34
     extremo
    0.33
     гало
    0.32
     defend
    0.32
     कीट
    0.31
     극
    0.31
     extreme
    0.31
     BF
    0.30
    POSITIVE LOGITS
    notification
    0.33
     Adj
    0.31
    theoretical
    0.30
    Countdown
    0.29
    Theoretical
    0.29
    Adj
    0.29
     சின்னமாக
    0.29
     scelta
    0.28
     finishers
    0.28
    YNAM
    0.28
    Activations Density 0.016%

    No Known Activations