© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75964
    Prev
    Next
    INDEX
    Explanations

    variable assignment or update

    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_31_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
     боро
    0.38
     obstructed
    0.35
     havas
    0.34
     अपन
    0.33
     hackers
    0.33
     tossed
    0.33
     hacked
    0.33
    鿓
    0.33
     tons
    0.33
    裹
    0.33
    POSITIVE LOGITS
    绎
    0.44
    issimus
    0.39
     प्रिंस
    0.38
    confirmation
    0.38
     ಸ
    0.38
    นาด
    0.37
    adeus
    0.37
    ！！！！
    0.37
    чили
    0.36
    சோ
    0.36
    Activations Density 0.001%

    No Known Activations