© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198907
    Prev
    Next
    INDEX
    Explanations

    player positions

    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_27_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
    Auth
    0.37
    Primary
    0.35
    ಕ್ತ
    0.35
     girth
    0.34
    Nation
    0.34
     primary
    0.33
    띄
    0.33
     Trabajo
    0.33
     T
    0.33
    assung
    0.33
    POSITIVE LOGITS
     disputes
    0.36
     ngược
    0.35
     informations
    0.35
     möjligt
    0.35
    amini
    0.35
     da
    0.34
     अल
    0.34
     KAL
    0.34
    informations
    0.34
     RID
    0.34
    Activations Density 0.001%

    No Known Activations