© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83102
    Prev
    Next
    INDEX
    Explanations

    someone/something/finally

    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_29_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
     Freestyle
    0.35
     ulter
    0.34
     дальней
    0.33
    影响
    0.33
     freestyle
    0.33
    general
    0.32
    𝘰
    0.32
    不大
    0.32
     further
    0.32
    ）；
    0.32
    POSITIVE LOGITS
     alguma
    0.42
     alguna
    0.41
     någon
    0.39
     няко
    0.38
    บ้าง
    0.38
    終於
    0.38
     എന്ത
    0.38
     rarely
    0.36
    ड़िया
    0.36
    嬪
    0.36
    Activations Density 0.029%

    No Known Activations