© 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. 15462
    Prev
    Next
    INDEX
    Explanations

    as

    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
     spineItem
    0.25
    吔
    0.23
     በፊት
    0.23
     влияние
    0.22
     инсу
    0.22
     irradiation
    0.21
    𝐆
    0.21
     wèi
    0.21
     мүмк
    0.21
    𝐾
    0.21
    POSITIVE LOGITS
    '
    0.23
    ach
    0.22
    ’
    0.20
    ak
    0.20
    wan
    0.19
    ots
    0.19
    ati
    0.18
    nick
    0.18
    nn
    0.18
    ene
    0.18
    Activations Density 0.014%

    No Known Activations