© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28858
    Prev
    Next
    INDEX
    Explanations

    reply or response to channel

    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_40_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
     пос
    0.43
    દય
    0.41
    筵
    0.40
     rendszer
    0.39
     Classified
    0.39
     веке
    0.38
    ImmediateContext
    0.38
    etary
    0.37
     pude
    0.37
    நாட்டில்
    0.37
    POSITIVE LOGITS
     concerned
    0.37
     Guan
    0.37
    Utility
    0.37
    (($
    0.36
     fuc
    0.36
    utility
    0.35
     utility
    0.35
    Success
    0.35
    Gu
    0.34
    şı
    0.34
    Activations Density 0.001%

    No Known Activations