© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194552
    Prev
    Next
    INDEX
    Explanations

    flying Air, applies to, tering

    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_9_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
     FAC
    0.50
    ين
    0.48
     pouce
    0.41
    ەد
    0.41
    ἂ
    0.41
    ্যেষ্ঠ
    0.40
     virtual
    0.40
     ALUMIN
    0.40
     AK
    0.38
    Ин
    0.38
    POSITIVE LOGITS
    ccncc
    0.50
     annunci
    0.50
    ture
    0.49
    renees
    0.49
     कार्य
    0.48
     نیا
    0.48
    families
    0.48
    रेशन
    0.48
    䉽
    0.47
    parseFloat
    0.47
    Activations Density 0.000%

    No Known Activations