© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138840
    Prev
    Next
    INDEX
    Explanations

    strands frame face

    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_37_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
     xhr
    0.39
    ុ
    0.38
    तें
    0.37
     brewer
    0.36
     Agen
    0.35
     ကု
    0.34
    xhr
    0.34
    θαν
    0.34
     recycle
    0.34
     せ
    0.33
    POSITIVE LOGITS
     frames
    1.23
     frame
    1.19
     framing
    1.13
    frame
    1.11
     Frame
    1.10
     Frames
    1.10
    Frames
    1.05
    Frame
    1.05
     framed
    1.05
     FRAME
    1.02
    Activations Density 0.002%

    No Known Activations