© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36648
    Prev
    Next
    INDEX
    Explanations

    file structure

    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_3_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
     I
    1.08
    i
    1.05
    ه
    1.02
    ed
    0.98
    a
    0.85
    ,
    0.82
    e
    0.81
     and
    0.80
     of
    0.80
    ۲
    0.78
    POSITIVE LOGITS
    sol
    0.61
    "$
    0.59
    panels
    0.59
    spin
    0.58
    ts
    0.57
    ayama
    0.57
    skap
    0.57
    가를
    0.57
    spiel
    0.56
    passes
    0.55
    Activations Density 0.019%

    No Known Activations