© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260482
    Prev
    Next
    INDEX
    Explanations

    accessibility features

    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_22_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
     صور
    0.46
     MCC
    0.40
     bú
    0.38
     gia
    0.37
    Bracketing
    0.37
    紺
    0.37
     Seeing
    0.36
    黑色
    0.36
     含
    0.36
     DCM
    0.36
    POSITIVE LOGITS
    ்சை
    0.46
     looms
    0.46
    ільки
    0.45
     tankers
    0.45
     wheels
    0.45
     exagger
    0.45
    lovl
    0.44
     underestimates
    0.44
     exaggerate
    0.43
     manages
    0.43
    Activations Density 0.001%

    No Known Activations