© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129899
    Prev
    Next
    INDEX
    Explanations

    grandparent

    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_6_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
     하지만
    0.89
    arni
    0.88
     لیکن
    0.83
    ärke
    0.82
    '
    0.80
    ’
    0.80
    ijing
    0.77
    ennan
    0.77
    ancy
    0.76
     लिहि
    0.76
    POSITIVE LOGITS
    t
    1.38
    ע
    1.21
    то
    1.19
    l
    1.15
    )
    1.12
    <0x80>
    1.10
    ט
    1.09
    b
    1.05
    c
    1.04
    ع
    1.03
    Activations Density 0.000%

    No Known Activations