© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170814
    Prev
    Next
    INDEX
    Explanations

    scala code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    under
    0.42
    LER
    0.40
    oma
    0.40
    [
    0.39
    into
    0.39
    Vertical
    0.38
    ικό
    0.38
    PM
    0.38
    Under
    0.38
    Center
    0.38
    POSITIVE LOGITS
     s
    0.50
     -------
    0.49
     auditing
    0.46
     -----
    0.45
     -----------
    0.44
     :::
    0.44
     ++
    0.42
     живу
    0.41
     cuantos
    0.41
     st
    0.41
    Activations Density 0.000%

    No Known Activations