© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139752
    Prev
    Next
    INDEX
    Explanations

    prefixes/fragments

    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_46_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
     L
    0.50
    Yak
    0.42
    </tfoot>
    0.42
    Camel
    0.40
     नारियल
    0.40
    camel
    0.40
    ミック
    0.39
     Yak
    0.39
    Ｌ
    0.39
     camel
    0.39
    POSITIVE LOGITS
     polyt
    0.41
     jr
    0.41
     py
    0.39
    ావ
    0.39
     Monro
    0.38
    pyrrolo
    0.38
     monochrom
    0.38
    py
    0.38
     Ach
    0.38
     pyruvate
    0.37
    Activations Density 0.025%

    No Known Activations