© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15975
    Prev
    Next
    INDEX
    Explanations

    Azkaban, Krabappel, Parseltongue

    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_15_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
    ):
    0.57
    :
    0.56
     member
    0.54
     possibili
    0.54
     titanium
    0.52
     lov
    0.50
     island
    0.50
     YANG
    0.50
     möj
    0.49
     monoch
    0.48
    POSITIVE LOGITS
    Ara
    0.54
     उत
    0.52
    褶
    0.51
    是为了
    0.51
    гія
    0.51
     예
    0.50
    ତା
    0.50
    ✞
    0.49
    咕
    0.49
     crawls
    0.49
    Activations Density 0.002%

    No Known Activations