© 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. 22064
    Prev
    Next
    INDEX
    Explanations

    _

    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
    .**
    0.47
    .”—
    0.43
     chopped
    0.42
     données
    0.42
     continuity
    0.42
    .—
    0.42
     donné
    0.41
     ethereum
    0.40
     ’
    0.39
     ther
    0.38
    POSITIVE LOGITS
    ~)
    0.47
    ,)
    0.47
    -)
    0.47
    -,
    0.46
    isolated
    0.45
    verified
    0.44
    content
    0.43
     -,
    0.42
    som
    0.41
    י
    0.41
    Activations Density 0.006%

    No Known Activations