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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 130518
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    แต่
    0.37
    াবণ
    0.36
     apprezz
    0.36
     insulating
    0.36
    Ἥ
    0.36
     appreciated
    0.35
    rnn
    0.35
    <unused70>
    0.34
    <unused48>
    0.34
     uppermost
    0.34
    POSITIVE LOGITS
    मध
    0.39
     ऑफर्स
    0.38
    INA
    0.37
     nasel
    0.36
     Kết
    0.36
     لقد
    0.36
     वास
    0.35
     Deux
    0.35
     WAT
    0.34
     согласно
    0.34
    Activations Density 0.000%

    No Known Activations