© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137033
    Prev
    Next
    INDEX
    Explanations

    pointing towards or at

    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
    sir
    0.57
     cornerstone
    0.57
     investors
    0.56
    е
    0.56
    ิก
    0.54
     allied
    0.54
     تحقیق
    0.54
    Investigations
    0.53
     uzman
    0.52
     assassinated
    0.52
    POSITIVE LOGITS
    ckt
    0.57
    }=\
    0.55
    sendBuf
    0.53
    افة
    0.51
    нную
    0.51
    ckte
    0.51
    דול
    0.50
    ্মদ
    0.49
    防止
    0.48
     ሁኔታ
    0.48
    Activations Density 0.002%

    No Known Activations