© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179555
    Prev
    Next
    INDEX
    Explanations

    names after uppercase letters

    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_24_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
     ángulos
    0.42
     análisis
    0.41
    inputSet
    0.38
     भर्त
    0.38
    ܥ
    0.38
    匹配
    0.38
     நிதி
    0.37
    modeling
    0.37
    דיה
    0.37
    𝗷
    0.37
    POSITIVE LOGITS
     offici
    0.41
    Recommended
    0.40
     offic
    0.38
    kel
    0.38
     Steep
    0.36
     gtag
    0.35
    休み
    0.35
    adore
    0.34
    fter
    0.34
    旲
    0.34
    Activations Density 0.000%

    No Known Activations