© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205933
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     сопер
    0.44
     ngủ
    0.38
     போட்டிய
    0.37
     nasled
    0.37
     respond
    0.37
    mour
    0.36
    榈
    0.36
    你说
    0.36
     उम्मीदवारों
    0.36
     yanıt
    0.36
    POSITIVE LOGITS
     absolutely
    0.45
    Absolutely
    0.42
     Make
    0.40
     absolutamente
    0.40
     TAT
    0.40
    absolutely
    0.40
     Sand
    0.39
     MA
    0.39
     Absolutely
    0.39
    Sand
    0.38
    Activations Density 0.004%

    No Known Activations