© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249514
    Prev
    Next
    INDEX
    Explanations

    social materials

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     (‘
    0.42
    odoxy
    0.41
     $\%$
    0.40
     pervasive
    0.40
    cies
    0.40
    OMET
    0.39
     ($(
    0.38
     $\#
    0.38
     unprofitable
    0.38
    蛀
    0.38
    POSITIVE LOGITS
    ుల
    0.43
     Kyl
    0.39
    Sac
    0.39
     Erl
    0.39
    IAS
    0.38
    nashville
    0.37
    ulman
    0.37
    ias
    0.36
    日閲覧
    0.36
    届
    0.36
    Activations Density 0.000%

    No Known Activations