© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63035
    Prev
    Next
    INDEX
    Explanations

    on

    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_59_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
    <<<
    0.43
    '><
    0.41
    íss
    0.41
    ॥
    0.39
    '(
    0.39
     prophyl
    0.39
    ема
    0.38
    '"
    0.38
    etically
    0.38
     જરૂ
    0.38
    POSITIVE LOGITS
     hand
    1.63
    手
    1.43
     손
    1.41
    손
    1.40
     Hand
    1.30
     دست
    1.30
    Hand
    1.21
    hand
    1.20
     手
    1.16
     mão
    1.16
    Activations Density 0.002%

    No Known Activations