© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1739
    Prev
    Next
    INDEX
    Explanations

    both 0 and 1

    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
     obstante
    0.31
     なく
    0.31
    Neighborhood
    0.30
     EXAMINATION
    0.29
    examination
    0.29
    ̹
    0.29
    ನಿರ್
    0.29
     '/',
    0.28
    ColorScheme
    0.28
     imageName
    0.28
    POSITIVE LOGITS
     wave
    0.41
     photons
    0.33
    Photon
    0.33
    wave
    0.33
     photon
    0.32
    eringen
    0.32
     Wave
    0.32
    波動
    0.32
     Electrons
    0.32
     Lu
    0.31
    Activations Density 0.014%

    No Known Activations