© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66606
    Prev
    Next
    INDEX
    Explanations

    STALKER, Diablo, Call of Pripyat

    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_41_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
    <unused47>
    0.39
     acheter
    0.38
    azie
    0.38
    <unused35>
    0.38
    <unused67>
    0.37
    <unused68>
    0.37
    యోజ
    0.36
    <unused2>
    0.36
    ジェクト
    0.36
    ච
    0.36
    POSITIVE LOGITS
    address
    0.37
     distortions
    0.37
     Macs
    0.34
     Ton
    0.34
     stalls
    0.34
    ূ
    0.34
     Dist
    0.33
     couches
    0.33
     szem
    0.33
     tongs
    0.33
    Activations Density 0.001%

    No Known Activations