© 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. 5865
    Prev
    Next
    INDEX
    Explanations

    terraform provider configuration

    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
     crim
    0.43
     Bras
    0.42
     criminality
    0.41
    쩝
    0.41
    nard
    0.40
     eight
    0.40
    ardt
    0.39
     Maguire
    0.38
     curled
    0.37
     bras
    0.37
    POSITIVE LOGITS
    æn
    0.42
    驁
    0.40
    ރ
    0.39
    notebook
    0.38
    protobuf
    0.37
     துணை
    0.37
     Notebook
    0.36
    Notebook
    0.35
    тельной
    0.33
     дове
    0.33
    Activations Density 0.002%

    No Known Activations