© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210861
    Prev
    Next
    INDEX
    Explanations

    `k8s.io/`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     Till
    0.50
     Designing
    0.48
     Agriculture
    0.48
     Think
    0.47
    <unused35>
    0.46
     Gloucester
    0.46
     Camel
    0.46
     જ્યારે
    0.46
     Gladstone
    0.46
     Pickett
    0.46
    POSITIVE LOGITS
    등
    0.45
     revis
    0.44
     altres
    0.43
     manuals
    0.43
     demoral
    0.43
    社會
    0.42
     ballads
    0.42
    social
    0.42
    우
    0.42
    ます
    0.41
    Activations Density 0.000%

    No Known Activations