© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214948
    Prev
    Next
    INDEX
    Explanations

    composite material or function

    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_5_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
    ர
    1.03
    ності
    1.01
    ல்
    1.00
    ллер
    0.99
    roon
    0.96
    ющих
    0.93
    ле
    0.92
     ampio
    0.91
     moguće
    0.91
    ర్థిక
    0.89
    POSITIVE LOGITS
    "
    1.44
    א
    1.30
    కు
    1.23
    我们
    1.12
    us
    1.11
    ก
    1.11
    ק
    1.09
    ()
    1.06
    (
    1.06
    of
    1.04
    Activations Density 0.001%

    No Known Activations