© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177835
    Prev
    Next
    INDEX
    Explanations

    intensity and scale

    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_29_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
     scalar
    0.40
     DateTime
    0.36
     Raster
    0.35
     pogod
    0.35
     pathologic
    0.34
    凸
    0.33
     کردیا
    0.32
    као
    0.32
    דו
    0.32
    или
    0.32
    POSITIVE LOGITS
    呥
    0.39
     prompting
    0.35
    ുകളിൽ
    0.34
    ᚗ
    0.34
     приез
    0.33
    調整
    0.33
    垀
    0.33
    Visiting
    0.32
    情報を
    0.31
    部に
    0.31
    Activations Density 0.004%

    No Known Activations