© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163463
    Prev
    Next
    INDEX
    Explanations

    code syntax generating random strings

    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_31_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
     غر
    0.38
     cade
    0.36
    वन
    0.36
    mangle
    0.36
    琹
    0.36
    (<
    0.35
    অভ
    0.35
    䙷
    0.35
    塢
    0.35
     дум
    0.34
    POSITIVE LOGITS
     Pos
    0.43
    idez
    0.40
    iela
    0.40
     Oxid
    0.39
    नेटरी
    0.39
    विला
    0.38
    oxid
    0.38
     Feeding
    0.38
     Complement
    0.37
     conveying
    0.36
    Activations Density 0.005%

    No Known Activations