© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238116
    Prev
    Next
    INDEX
    Explanations

    but also

    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
    uto
    0.40
     ș
    0.39
    ग्राउंड
    0.38
    ?;
    0.37
     ਮ
    0.37
     ecce
    0.37
    🐾
    0.37
    SIMPLEX
    0.37
    itag
    0.37
    ➵
    0.37
    POSITIVE LOGITS
     apologised
    0.42
    称
    0.41
     Clarks
    0.41
     Losing
    0.41
    不管
    0.38
     defending
    0.36
     apologise
    0.36
     niew
    0.36
     Royals
    0.36
     держави
    0.36
    Activations Density 0.004%

    No Known Activations