© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214662
    Prev
    Next
    INDEX
    Explanations

    Computer-Aided Design

    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_5_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
    ى
    1.07
    ,
    1.02
    p
    0.96
    ні
    0.84
    v
    0.82
    de
    0.79
    т
    0.77
    ien
    0.75
    type
    0.74
    л
    0.72
    POSITIVE LOGITS
    ה
    0.83
    uire
    0.80
    el
    0.79
    이었다
    0.75
    ありますが
    0.75
    anın
    0.74
    ંબ
    0.73
    ol
    0.72
    يا
    0.72
    اوی
    0.72
    Activations Density 0.000%

    No Known Activations