© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126338
    Prev
    Next
    INDEX
    Explanations

    presented structure

    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_3_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
    0.77
     वस्तू
    0.66
    𝟎
    0.64
     آهن
    0.63
    ッド
    0.61
    Das
    0.60
    quipe
    0.60
    <0x80>
    0.59
    thirds
    0.58
    리가
    0.58
    POSITIVE LOGITS
    ী
    0.80
    ين
    0.74
    ي
    0.73
    ור
    0.71
    ation
    0.71
    い
    0.70
    י
    0.69
    ı
    0.67
    ة
    0.66
    ת
    0.65
    Activations Density 0.001%

    No Known Activations