© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204364
    Prev
    Next
    INDEX
    Explanations

    after list items

    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_25_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
     collaboratively
    0.39
    绡
    0.39
     housing
    0.38
     basis
    0.38
     Liebe
    0.37
     Basis
    0.37
     Х
    0.37
     Aby
    0.37
     Probate
    0.36
     Grundlage
    0.36
    POSITIVE LOGITS
    scotch
    0.46
     egyes
    0.41
    spac
    0.41
    𝚛
    0.40
    prof
    0.39
    lerim
    0.39
     mappa
    0.38
     certificado
    0.37
    sor
    0.37
    estellt
    0.37
    Activations Density 0.005%

    No Known Activations