© 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. 157797
    Prev
    Next
    INDEX
    Explanations

    Quincy

    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
     tám
    0.96
    <0x8B>
    0.95
    <0xB8>
    0.94
     benöt
    0.94
    <0xA6>
    0.91
     директора
    0.91
     څنګه
    0.90
    <0x80>
    0.89
     второй
    0.88
     рам
    0.88
    POSITIVE LOGITS
    ad
    1.73
    us
    1.67
    as
    1.61
    le
    1.45
    ly
    1.37
    ר
    1.36
    ।
    1.35
    ur
    1.31
    th
    1.31
    ת
    1.30
    Activations Density 0.000%

    No Known Activations