© 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. 216368
    Prev
    Next
    INDEX
    Explanations

    emphasize immediacy or formality

    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
     রঙের
    0.41
     invert
    0.40
     inverted
    0.39
     darker
    0.39
     perpendicularly
    0.38
     красный
    0.37
    縦
    0.37
     Photo
    0.37
     Bie
    0.37
     Photography
    0.36
    POSITIVE LOGITS
    cientes
    0.37
    INF
    0.35
    ब्रा
    0.35
    etically
    0.35
     treaty
    0.34
    टिक
    0.34
     Bedingungen
    0.34
    elya
    0.34
    <unused27>
    0.34
    പി
    0.34
    Activations Density 0.035%

    No Known Activations