© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79204
    Prev
    Next
    INDEX
    Explanations

    contexto

    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_29_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
     अथवा
    0.42
     alguno
    0.36
    あるいは
    0.36
    etches
    0.35
    聚
    0.35
     subdivisions
    0.35
    ishw
    0.35
     మాత్రం
    0.34
    reszt
    0.34
    NES
    0.34
    POSITIVE LOGITS
    給
    0.38
     අඩු
    0.38
     دانش
    0.38
     문제를
    0.38
     അഭ
    0.38
     Antip
    0.37
     க
    0.37
     Overflow
    0.37
     naše
    0.36
     Utd
    0.36
    Activations Density 0.013%

    No Known Activations