© 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. 219072
    Prev
    Next
    INDEX
    Explanations

    plant responses and development

    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
    omain
    0.42
     Latin
    0.40
     खून
    0.39
     ELISA
    0.39
     выполнение
    0.39
    竞
    0.38
    ']),
    0.38
     stakeholder
    0.38
     Tiempo
    0.38
     Hem
    0.37
    POSITIVE LOGITS
     $\{(
    0.39
     農
    0.38
     হবেনা
    0.37
    ziná
    0.37
     witnesses
    0.36
     traversed
    0.36
     أهم
    0.35
    廁
    0.35
     اهم
    0.35
     cauldron
    0.34
    Activations Density 0.002%

    No Known Activations