© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42948
    Prev
    Next
    INDEX
    Explanations

    housing details

    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_22_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
     cardí
    0.32
     intolerance
    0.31
    sizing
    0.31
    Ζ
    0.31
     restauración
    0.30
    𝘇
    0.29
    ız
    0.29
    μός
    0.29
    unda
    0.28
    谛
    0.28
    POSITIVE LOGITS
     waste
    0.34
     Joplin
    0.33
     eyel
    0.32
     выбро
    0.32
     Josephson
    0.31
     Photographer
    0.31
     dubai
    0.30
     প্যাকে
    0.30
     حداقل
    0.30
     nop
    0.29
    Activations Density 0.021%

    No Known Activations