© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130594
    Prev
    Next
    INDEX
    Explanations

    bellwether

    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_6_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
    У
    0.98
     момент
    0.84
    ărilor
    0.82
    (
    0.82
    9
    0.81
    December
    0.80
    About
    0.79
     размере
    0.79
    А
    0.77
    نا
    0.76
    POSITIVE LOGITS
    ه
    1.75
    et
    1.46
    a
    1.43
    ু
    1.38
    া
    1.32
    ה
    1.25
    ار
    1.17
    ol
    1.16
    e
    1.16
     are
    1.15
    Activations Density 0.000%

    No Known Activations