© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139773
    Prev
    Next
    INDEX
    Explanations

    ignore input characters

    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_12_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
     poodle
    0.52
     Zürich
    0.48
    ט
    0.48
     kaleidoscopic
    0.47
     toiletries
    0.47
     óleo
    0.46
     smoothie
    0.45
    új
    0.45
     École
    0.43
     USE
    0.43
    POSITIVE LOGITS
    avr
    0.45
     ihnen
    0.44
    edian
    0.44
    Bsky
    0.44
    ˹
    0.43
    u
    0.43
    eti
    0.43
     ನಾನು
    0.43
    esh
    0.42
    adhy
    0.42
    Activations Density 0.001%

    No Known Activations