© 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. 57982
    Prev
    Next
    INDEX
    Explanations

    Project Chimera

    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
    ни
    0.58
    ва
    0.58
    We
    0.56
    로
    0.54
    те
    0.54
    FirstOrDefault
    0.53
    eno
    0.52
    (),
    0.51
    BrNO
    0.51
    不
    0.51
    POSITIVE LOGITS
     hydrogen
    0.64
     just
    0.61
     vállalat
    0.61
     its
    0.60
     hydroxyl
    0.58
     tradicional
    0.58
    hydrox
    0.57
     conventional
    0.57
     définit
    0.57
     sheet
    0.57
    Activations Density 0.000%

    No Known Activations