© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236702
    Prev
    Next
    INDEX
    Explanations

    shapes

    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_46_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
     rip
    0.39
    Rip
    0.38
    IX
    0.38
     Chim
    0.37
    igit
    0.37
     Zoom
    0.36
    Chim
    0.36
    룬
    0.36
    Zoom
    0.36
     Rip
    0.36
    POSITIVE LOGITS
    sph
    0.49
    Sph
    0.46
     sph
    0.45
    𝙘
    0.44
     spherical
    0.43
     sphing
    0.42
     Sph
    0.40
    gad
    0.38
    浮
    0.37
    sphinx
    0.36
    Activations Density 0.001%

    No Known Activations