© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132644
    Prev
    Next
    INDEX
    Explanations

    Hyp

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    pot
    0.56
    POT
    0.47
    폿
    0.47
     pot
    0.46
    鉢
    0.45
    poles
    0.44
     Potts
    0.44
    ሱን
    0.44
    pots
    0.44
     Pott
    0.44
    POSITIVE LOGITS
     Banc
    0.43
     Not
    0.42
     Land
    0.42
    днев
    0.42
     pension
    0.40
     Pension
    0.40
    Not
    0.39
    胺
    0.38
    Pt
    0.38
     नॉ
    0.38
    Activations Density 0.001%

    No Known Activations