© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5801
    Prev
    Next
    INDEX
    Explanations

    examples are helpful

    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_39_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
    acles
    0.43
     دیکھا
    0.38
     категорії
    0.36
     অবজার
    0.36
    CreationFailed
    0.36
    閲
    0.36
    va
    0.35
     dear
    0.35
     ②
    0.35
    ⓡ,
    0.35
    POSITIVE LOGITS
     carreras
    0.40
     licensure
    0.38
     charts
    0.38
     ভারসাম
    0.38
     melden
    0.37
     হাম
    0.37
     dimin
    0.37
     chartered
    0.37
     help
    0.36
     chart
    0.36
    Activations Density 0.009%

    No Known Activations