© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178655
    Prev
    Next
    INDEX
    Explanations

    list initialization

    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_29_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
     Hue
    0.19
     역
    0.19
    Hue
    0.18
     Acknowledg
    0.17
     analytic
    0.17
    য়াল
    0.17
    ٣
    0.17
    Appear
    0.17
     abbreviations
    0.17
     मांझी
    0.17
    POSITIVE LOGITS
     rép
    0.20
     multiplets
    0.20
    organe
    0.19
    湳
    0.19
     സ്വാ
    0.18
    ходу
    0.18
    mina
    0.18
    อื่น
    0.18
     takiego
    0.18
    꽝
    0.18
    Activations Density 0.007%

    No Known Activations