© 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. 83026
    Prev
    Next
    INDEX
    Explanations

    Neanderthals and Space Marines

    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
    in
    2.16
    t
    2.05
    at
    1.77
    sı
    1.63
    ták
    1.60
    র
    1.59
    tahun
    1.56
    st
    1.55
    ی
    1.55
    tive
    1.53
    POSITIVE LOGITS
     on
    1.42
    é
    1.37
    ian
    1.22
    .
    1.17
    ere
    1.11
    ax
    1.08
    ő
    1.08
    ior
    1.07
    ilo
    1.06
     leistungs
    1.01
    Activations Density 0.000%

    No Known Activations