© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9547
    Prev
    Next
    INDEX
    Explanations

    Alabama, Mississippi, rivers, beaches

    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_13_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
    ْ
    0.38
    ار
    0.37
     salty
    0.36
     Louisiana
    0.36
     Mississippi
    0.35
    ﯽ
    0.35
     required
    0.34
    ﺘ
    0.34
     Не
    0.34
     do
    0.33
    POSITIVE LOGITS
     computeEncoder
    0.39
    ogenicity
    0.39
     vanwege
    0.38
    ඩි
    0.36
     indag
    0.35
    ance
    0.34
    бург
    0.34
    daniel
    0.33
     ⇒
    0.33
    õ
    0.33
    Activations Density 0.001%

    No Known Activations