© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161086
    Prev
    Next
    INDEX
    Explanations

    aspects of

    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_2_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
    h
    1.59
    ৫
    1.37
    х
    1.16
    ем
    1.15
    рила
    1.13
    hx
    1.06
    ας
    1.05
    чи
    1.02
    的技术
    1.01
    зыка
    1.01
    POSITIVE LOGITS
     to
    1.68
    2
    1.50
     is
    1.44
     a
    1.41
    IT
    1.40
    O
    1.38
    R
    1.35
     be
    1.30
    IL
    1.30
     with
    1.29
    Activations Density 0.005%

    No Known Activations