© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39294
    Prev
    Next
    INDEX
    Explanations

    shadows lengthening, creeping, dancing

    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_11_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
     quotas
    0.52
    ف
    0.52
    Π
    0.52
    绮
    0.49
    ämä
    0.49
     ಇದ
    0.48
    과는
    0.48
    abilistic
    0.48
     demostrar
    0.47
     flashbacks
    0.47
    POSITIVE LOGITS
    AdType
    0.61
    ினான்
    0.59
    en
    0.58
     GUIContent
    0.58
     ไม่มี
    0.57
    ⺀
    0.57
     فرزند
    0.56
    מין
    0.55
    ใ
    0.55
    Atom
    0.55
    Activations Density 0.006%

    No Known Activations