© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167135
    Prev
    Next
    INDEX
    Explanations

    closing of messages

    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_34_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
    ఖ
    0.39
    Always
    0.39
    lbrakk
    0.38
     Wszyst
    0.36
    థ
    0.36
    ენტ
    0.35
    pull
    0.34
     ভুট
    0.34
     Always
    0.34
     праців
    0.33
    POSITIVE LOGITS
    ARAJYA
    0.40
    㹮
    0.36
    ooka
    0.36
    ">\
    0.35
    raines
    0.35
    শীর
    0.34
     زد
    0.33
     "~
    0.33
    еме
    0.33
     पुल्लिंग
    0.33
    Activations Density 0.001%

    No Known Activations