© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167083
    Prev
    Next
    INDEX
    Explanations

    National

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     human
    0.40
     dom
    0.40
    dom
    0.38
    asilkan
    0.38
     Under
    0.38
     Domino
    0.37
    팽
    0.37
    ায়ক
    0.37
     domes
    0.37
     पाठ
    0.36
    POSITIVE LOGITS
    Share
    0.55
    share
    0.51
     share
    0.47
    Sexual
    0.47
     यौन
    0.46
     Share
    0.45
    udian
    0.43
    Y
    0.41
    SHARE
    0.40
     sexual
    0.40
    Activations Density 0.002%

    No Known Activations