© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205533
    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_6_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
    in
    1.23
    u
    1.18
    n
    1.12
    g
    1.08
    ar
    1.06
    f
    0.98
    gents
    0.98
    Chem
    0.95
    innt
    0.95
    ants
    0.94
    POSITIVE LOGITS
     doua
    1.20
     دليل
    1.13
    ي
    1.13
     persiste
    1.09
     může
    1.09
     ي
    1.05
     utilize
    1.04
    <0x0D>
    1.03
    </b>
    1.02
     esté
    1.02
    Activations Density 0.000%

    No Known Activations