© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157738
    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_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
    '
    1.61
    K
    1.34
    {
    1.33
    er
    1.32
    )
    1.26
    H
    1.12
    ävä
    1.10
    W
    1.10
     och
    1.09
    kan
    1.08
    POSITIVE LOGITS
    л
    2.31
    ש
    1.44
    س
    1.38
     powied
    1.36
    ล
    1.22
    ปี
    1.19
    اً
    1.17
    ل
    1.17
    s
    1.16
    }).
    1.14
    Activations Density 0.000%

    No Known Activations