© 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. 122626
    Prev
    Next
    INDEX
    Explanations

    relearn

    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
    ek
    0.96
    K
    0.93
    al
    0.92
     released
    0.83
    ing
    0.80
    as
    0.78
    N
    0.78
    ed
    0.75
    o
    0.74
    e
    0.73
    POSITIVE LOGITS
     lágrimas
    0.96
    کن
    0.91
    ні
    0.87
    л
    0.87
    ते
    0.86
    که
    0.82
    պ
    0.74
    ке
    0.73
    ных
    0.73
     активности
    0.73
    Activations Density 0.001%

    No Known Activations