© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235690
    Prev
    Next
    INDEX
    Explanations

    scanf input using %d

    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_32_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
     കര
    0.36
    ovod
    0.34
    frontend
    0.33
     manic
    0.33
    acara
    0.32
     f
    0.32
    POSITORY
    0.31
     આન
    0.31
    ishima
    0.31
     γεν
    0.31
    POSITIVE LOGITS
    タウン
    0.38
    はお
    0.37
     stdin
    0.37
     loob
    0.36
    ০০০
    0.35
    origines
    0.34
    తారు
    0.34
     bari
    0.33
    芮
    0.33
     Utah
    0.32
    Activations Density 0.001%

    No Known Activations