© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1080
    Prev
    Next
    INDEX
    Explanations

    same as

    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_40_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
    ielle
    0.52
    ayla
    0.47
    ELLE
    0.44
    Michelle
    0.44
    elle
    0.43
    eya
    0.43
    ѐ
    0.42
    ria
    0.42
    jha
    0.42
    ē
    0.40
    POSITIVE LOGITS
     ones
    0.54
    exact
    0.42
     exact
    0.42
     Ones
    0.39
    もの
    0.38
    mutex
    0.37
    แท
    0.37
    fallback
    0.36
    ून्य
    0.36
     всеми
    0.36
    Activations Density 0.350%

    No Known Activations