© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54412
    Prev
    Next
    INDEX
    Explanations

    all, future tense, lever, atom

    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_30_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
    دو
    0.39
     fondamentale
    0.38
     fasilitas
    0.38
     transpired
    0.36
    يدي
    0.36
     gestational
    0.36
     gratis
    0.36
    嶋
    0.36
    罡
    0.36
    дія
    0.35
    POSITIVE LOGITS
    angered
    0.38
     või
    0.38
    ｌ
    0.37
    ndo
    0.36
    ఖా
    0.35
     Baltimore
    0.35
    spray
    0.34
    EndDate
    0.33
     హైదర్
    0.33
     Mary
    0.33
    Activations Density 0.000%

    No Known Activations