© 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. 111553
    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
    8
    1.16
     you
    1.14
     ferv
    1.09
    ы
    1.05
     was
    1.04
    ের
    1.04
    9
    1.03
    с
    1.01
    "
    0.99
     aventure
    0.97
    POSITIVE LOGITS
    i
    1.62
    an
    1.51
    a
    1.38
    il
    1.23
    ਾ
    1.17
    ে
    1.16
    rans
    1.09
    ان
    1.08
    er
    1.05
    า
    1.05
    Activations Density 0.000%

    No Known Activations