© 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. 111002
    Prev
    Next
    INDEX
    Explanations

    can you

    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
    ো
    0.88
    preco
    0.86
    生まれた
    0.86
    j
    0.86
     retorn
    0.84
    Cllr
    0.84
     antica
    0.83
     berasal
    0.83
    <unused60>
    0.82
    )]
    0.82
    POSITIVE LOGITS
    s
    2.02
    ی
    1.61
    on
    1.50
    ง
    1.39
    ים
    1.37
    ط
    1.23
     was
    1.21
    اء
    1.21
    dır
    1.21
    اي
    1.20
    Activations Density 0.011%

    No Known Activations