© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159053
    Prev
    Next
    INDEX
    Explanations

    aging, plagued

    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
    g
    1.53
    h
    1.39
    a
    1.23
    p
    1.22
    s
    1.20
    re
    1.19
    al
    1.12
    y
    1.11
    b
    1.09
    ra
    1.05
    POSITIVE LOGITS
    った
    1.21
    지
    1.17
    فين
    1.16
    ر
    1.15
    И
    1.14
    އ
    1.05
    ವ
    1.05
    ت
    1.04
     spindles
    1.03
    지에
    1.03
    Activations Density 0.000%

    No Known Activations