© 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. 79506
    Prev
    Next
    INDEX
    Explanations

    json schema definitions

    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
     labors
    0.42
    ****/
    0.39
    隴
    0.39
     embroidery
    0.39
     Epidemiology
    0.38
     Embro
    0.38
     bee
    0.38
    Ϭ
    0.37
    槃
    0.37
     Alk
    0.37
    POSITIVE LOGITS
    Preference
    0.40
     afsl
    0.39
    Filter
    0.37
    Dock
    0.36
    غاز
    0.36
    Locked
    0.36
    সেল
    0.36
    Sel
    0.35
    Vent
    0.35
    Closure
    0.35
    Activations Density 0.000%

    No Known Activations