© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242780
    Prev
    Next
    INDEX
    Explanations

    left or right

    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_40_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
    maxim
    0.44
    reté
    0.41
     manifestly
    0.41
    レスト
    0.40
     devad
    0.39
    跻
    0.39
     maximization
    0.39
     tỏ
    0.39
    ristown
    0.38
     постепенно
    0.38
    POSITIVE LOGITS
     front
    0.42
    equation
    0.39
    xE
    0.39
     equation
    0.38
     Front
    0.38
     Stru
    0.38
    cInfo
    0.38
    용한
    0.38
     frontal
    0.37
    [@
    0.37
    Activations Density 0.000%

    No Known Activations