© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1812
    Prev
    Next
    INDEX
    Explanations

    alpha particles and nucleus

    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_39_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
    idencia
    0.43
     cofactor
    0.43
     optics
    0.42
     olímp
    0.40
     biotechnology
    0.40
    消
    0.39
    علوم
    0.39
     óptica
    0.38
     optic
    0.37
    ^*
    0.37
    POSITIVE LOGITS
    Alpha
    0.63
     Alpha
    0.61
     alpha
    0.60
    alpha
    0.55
     alphas
    0.52
    Beta
    0.51
     Alph
    0.50
    Alph
    0.49
     nucleus
    0.47
     alph
    0.46
    Activations Density 0.087%

    No Known Activations