© 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
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165292
    Prev
    Next
    INDEX
    Explanations

    tasks :

    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
     ή
    0.54
    xls
    0.54
    g
    0.54
    es
    0.53
    ka
    0.53
    so
    0.51
    3
    0.51
    9
    0.51
    0
    0.51
    ethoven
    0.50
    POSITIVE LOGITS
    ედერ
    0.52
     Adik
    0.52
     Customized
    0.52
    тике
    0.51
     broadcasters
    0.50
     შემთხვევ
    0.50
     சினி
    0.50
     pierde
    0.50
    Ꮘ
    0.50
     NSP
    0.49
    Activations Density 0.001%

    No Known Activations