© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242321
    Prev
    Next
    INDEX
    Explanations

    estate distribution and handling

    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_40_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
     অস
    0.41
     luận
    0.39
    মাম
    0.39
     لاع
    0.38
    攽
    0.38
     law
    0.37
    financial
    0.37
    GOND
    0.37
    textured
    0.37
    逪
    0.36
    POSITIVE LOGITS
     settle
    0.44
     synth
    0.38
     synthet
    0.38
     settled
    0.38
     synt
    0.37
     toilette
    0.37
     decidir
    0.37
     संश्लेषण
    0.36
     Synt
    0.36
    ucid
    0.36
    Activations Density 0.003%

    No Known Activations