© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119545
    Prev
    Next
    INDEX
    Explanations

    URLs or page numbers

    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_27_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
     listings
    0.42
     stays
    0.40
    ,
    0.36
     sprinkles
    0.36
     الده
    0.36
     breasts
    0.35
    stays
    0.35
     llamas
    0.35
    ων
    0.35
    |+
    0.35
    POSITIVE LOGITS
    mapKey
    0.45
    璈
    0.44
     destroying
    0.42
     설정
    0.42
     Erfol
    0.42
     Dangerous
    0.42
     dangerous
    0.41
     gefähr
    0.41
     Setting
    0.41
     발생하는
    0.41
    Activations Density 0.000%

    No Known Activations