© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201262
    Prev
    Next
    INDEX
    Explanations

    risk register

    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_12_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
    巉
    0.56
     دہشت
    0.53
    ခြ
    0.51
    shares
    0.49
    つ
    0.49
    ח
    0.48
    酯
    0.48
    un
    0.48
    et
    0.47
    em
    0.47
    POSITIVE LOGITS
     stimulation
    0.55
     hypnotic
    0.54
    娥
    0.54
     petitions
    0.52
     tooling
    0.52
    ivé
    0.52
     investig
    0.52
     destra
    0.49
     biomass
    0.49
     darb
    0.49
    Activations Density 0.011%

    No Known Activations