© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14471
    Prev
    Next
    INDEX
    Explanations

    spray can contents

    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_13_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
    s
    0.53
     Algorithm
    0.52
     Amar
    0.52
     l
    0.51
    insights
    0.49
     articular
    0.48
    on
    0.48
     b
    0.47
     observable
    0.47
     WebView
    0.47
    POSITIVE LOGITS
     distanza
    0.55
     Childhood
    0.53
    敂
    0.52
    多个
    0.52
    ші
    0.51
    傅
    0.50
     Reck
    0.49
    myForm
    0.49
    韜
    0.49
    ದಲ್ಲಿ
    0.49
    Activations Density 0.010%

    No Known Activations