© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35508
    Prev
    Next
    INDEX
    Explanations

    Iran Hostage Crisis

    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
    Truman
    0.37
    우
    0.36
     சுவா
    0.36
    Walk
    0.35
     Swanson
    0.35
     Oka
    0.35
     дан
    0.34
    Hoy
    0.34
     우
    0.34
     Changer
    0.34
    POSITIVE LOGITS
     indef
    0.41
    histor
    0.39
     histor
    0.38
    солю
    0.35
     incumbent
    0.34
     dehydration
    0.34
    ᱘
    0.34
     rozw
    0.33
     বৈধ
    0.33
    ╝
    0.33
    Activations Density 0.000%

    No Known Activations