© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165851
    Prev
    Next
    INDEX
    Explanations

    identifying or referencing specific characters/entities

    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_31_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
    教学
    0.26
    Teach
    0.26
    Assemble
    0.25
     ASSEMBLY
    0.25
     بتوان
    0.24
    茶
    0.24
    nosť
    0.24
     組
    0.24
    嶈
    0.24
    Toy
    0.24
    POSITIVE LOGITS
     servent
    0.25
     කෙ
    0.25
    colored
    0.25
     Capp
    0.24
     undes
    0.24
     verticale
    0.24
     függ
    0.23
     erzählt
    0.23
     Bentley
    0.23
     ইন্দুর
    0.23
    Activations Density 0.004%

    No Known Activations