© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205613
    Prev
    Next
    INDEX
    Explanations

    centuries

    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
    –
    0.43
     late
    0.43
    late
    0.42
    ‐
    0.42
    $-$,
    0.41
    ның
    0.40
    -
    0.40
    \{(
    0.39
    ––
    0.39
     $-$
    0.37
    POSITIVE LOGITS
     century
    0.49
    世紀
    0.47
    世纪
    0.46
     Century
    0.43
     recommendations
    0.42
    recommend
    0.41
    century
    0.40
     Ree
    0.40
     member
    0.40
     siècle
    0.40
    Activations Density 0.001%

    No Known Activations