© 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. 165396
    Prev
    Next
    INDEX
    Explanations

    bangers, music, games, strong liking

    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
    ைகளால்
    0.49
    money
    0.48
    ing
    0.47
     இயந்திர
    0.47
    urte
    0.46
    outen
    0.46
    Մ
    0.46
     વૈ
    0.46
    rown
    0.45
    ﻠ
    0.45
    POSITIVE LOGITS
    Xaml
    0.52
     KLM
    0.52
    ค่ะ
    0.50
     EMB
    0.50
     permittee
    0.49
     parrots
    0.49
     huz
    0.49
     Olim
    0.48
     communists
    0.47
     EtOAc
    0.47
    Activations Density 0.000%

    No Known Activations