© 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. 45035
    Prev
    Next
    INDEX
    Explanations

    setting breakpoints

    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
     like
    0.39
    ustos
    0.38
     blame
    0.38
    Quran
    0.37
     resulted
    0.37
     덕
    0.37
    тах
    0.36
    తిరే
    0.36
    Sha
    0.36
     significantly
    0.36
    POSITIVE LOGITS
    㶱
    0.46
     collo
    0.40
     coltiv
    0.39
    ༈
    0.39
     Finder
    0.39
    媇
    0.39
    䡓
    0.39
    媤
    0.38
     apprend
    0.38
     glPushMatrix
    0.38
    Activations Density 0.000%

    No Known Activations