© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80724
    Prev
    Next
    INDEX
    Explanations

    tree data structures

    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_0_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
     I
    2.44
    '
    2.19
    ä
    2.13
    ри
    1.74
    -
    1.70
    "
    1.67
     can
    1.64
    at
    1.59
     was
    1.56
    ва
    1.52
    POSITIVE LOGITS
    코
    1.35
    𝘥
    1.31
    티
    1.30
    ش
    1.29
    ᱘
    1.20
    ש
    1.19
    އ
    1.19
    드
    1.18
    是由
    1.17
    ਸ
    1.16
    Activations Density 0.002%

    No Known Activations