© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119821
    Prev
    Next
    INDEX
    Explanations

    `say`

    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_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
     immaterial
    0.44
    ("**
    0.40
    Waiting
    0.36
    Wrapping
    0.36
    Alexandra
    0.36
    antation
    0.36
    +="
    0.35
    avr
    0.35
    unsplash
    0.35
    hoo
    0.35
    POSITIVE LOGITS
    渎
    0.39
     রেজিস্ট
    0.38
    лод
    0.38
    িসে
    0.38
    设施
    0.36
     journée
    0.36
     rapidez
    0.36
     droughts
    0.35
     dryness
    0.35
     paz
    0.35
    Activations Density 0.000%

    No Known Activations