© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194909
    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_27_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
    BorderStyle
    0.42
    MaxScaler
    0.42
    Merging
    0.40
    Wrapping
    0.39
    Clazz
    0.39
    ిత
    0.38
     **/
    0.37
     가정
    0.37
     Metrics
    0.37
     Wrapping
    0.37
    POSITIVE LOGITS
    endan
    0.47
    new
    0.46
    state
    0.45
    w
    0.44
    better
    0.44
     новый
    0.43
    send
    0.43
    material
    0.43
    helpful
    0.42
    sel
    0.42
    Activations Density 0.000%

    No Known Activations