© 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. 210705
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    on
    1.60
    al
    1.44
    л
    1.38
    ल
    1.30
    ע
    1.28
    is
    1.23
    ש
    1.21
    as
    1.18
    am
    1.17
    ah
    1.17
    POSITIVE LOGITS
    >
    1.17
     projeto
    0.93
    確保
    0.91
    égard
    0.89
    ва
    0.88
    اري
    0.86
    ется
    0.86
     опреде
    0.84
     могла
    0.81
     разрабо
    0.81
    Activations Density 0.000%

    No Known Activations