© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13600
    Prev
    Next
    INDEX
    Explanations

    short story

    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
     send
    0.55
    Send
    0.54
     Send
    0.53
     SEND
    0.50
    SEND
    0.48
    send
    0.47
    送
    0.46
     sending
    0.45
     Sending
    0.44
     sends
    0.42
    POSITIVE LOGITS
    Geplaatst
    0.38
     posted
    0.37
    onyms
    0.37
    鹛
    0.36
    ouncement
    0.36
    पूर्व
    0.36
    ទេស
    0.36
     साक्षी
    0.35
     complimented
    0.35
    implantation
    0.35
    Activations Density 0.023%

    No Known Activations