© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164014
    Prev
    Next
    INDEX
    Explanations

    kitchen + bar

    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_13_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
     】,
    0.50
     を
    0.48
     inhomogeneities
    0.47
    )}_{\
    0.46
    ┗
    0.46
    Ռ
    0.45
    LOTRE
    0.44
     ー
    0.44
     дыха
    0.43
     innov
    0.43
    POSITIVE LOGITS
    figur
    0.47
    婚姻
    0.45
    pik
    0.45
    prone
    0.44
    cluster
    0.44
     como
    0.43
    function
    0.43
     confounded
    0.42
    dans
    0.42
    ור
    0.41
    Activations Density 0.000%

    No Known Activations