© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176835
    Prev
    Next
    INDEX
    Explanations

    Correct

    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_24_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
    ▹
    0.28
    Compet
    0.28
    承认
    0.28
    承認
    0.27
    NED
    0.27
    COMP
    0.25
    compet
    0.25
     memenuhi
    0.25
    estown
    0.25
    Camp
    0.25
    POSITIVE LOGITS
     சில
    0.29
     продовжу
    0.28
    的其他
    0.28
     bö
    0.27
     벌
    0.27
     שלא
    0.27
     नये
    0.27
     Otros
    0.26
     provas
    0.26
     ovviamente
    0.26
    Activations Density 0.005%

    No Known Activations