© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83567
    Prev
    Next
    INDEX
    Explanations

    reducible, ridiculed, lifeless

    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_0_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
    ت
    1.55
    ї
    1.45
    ী
    1.44
    ات
    1.43
    ı
    1.43
    ться
    1.41
    า
    1.40
    ä
    1.38
    ט
    1.38
    но
    1.34
    POSITIVE LOGITS
    The
    1.24
     is
    1.20
    RO
    1.16
    the
    1.13
    LAW
    1.10
    ש
    1.08
    z
    1.07
    MP
    1.02
    LAN
    1.00
    GROW
    0.99
    Activations Density 0.001%

    No Known Activations