© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60125
    Prev
    Next
    INDEX
    Explanations

    URLs and 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_59_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
    **
    0.48
    *
    0.45
     Tactics
    0.42
    *-
    0.41
     Training
    0.39
    \
    0.39
     (!)
    0.39
     Time
    0.39
     Practices
    0.39
     comme
    0.38
    POSITIVE LOGITS
    ⟋
    0.45
    ihu
    0.42
    ellt
    0.42
    owano
    0.40
    nale
    0.39
    anken
    0.39
    eer
    0.39
    isiert
    0.39
    /}{
    0.38
    ebe
    0.38
    Activations Density 0.001%

    No Known Activations