© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44985
    Prev
    Next
    INDEX
    Explanations

    Spanish and names/titles

    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
     Bridgeport
    0.57
    𝑨
    0.55
    𝑭
    0.54
     F
    0.53
     Amtrak
    0.52
     ((
    0.51
     হয়ে
    0.51
     ፍ
    0.50
     美国
    0.49
     未来
    0.49
    POSITIVE LOGITS
    common
    0.55
    lors
    0.55
    els
    0.55
    ób
    0.54
    َح
    0.54
    स्‍
    0.54
    ngths
    0.53
    datos
    0.52
     lanzamiento
    0.52
    qs
    0.52
    Activations Density 0.004%

    No Known Activations