© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236692
    Prev
    Next
    INDEX
    Explanations

    d

    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_25_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
     laughable
    0.43
     à
    0.43
     ironic
    0.42
     za
    0.40
     জানাতে
    0.40
     AFI
    0.39
     á
    0.39
     sauv
    0.39
     cả
    0.38
     recommended
    0.38
    POSITIVE LOGITS
    মুসল
    0.39
    Primer
    0.36
    Styled
    0.34
    Convolution
    0.34
    Include
    0.34
    িয়াছিল
    0.33
    Holstein
    0.33
    PartResult
    0.33
    푞
    0.33
    呋
    0.33
    Activations Density 0.001%

    No Known Activations