© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233464
    Prev
    Next
    INDEX
    Explanations

    August 6th

    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_32_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
     Bru
    0.37
    డ్డు
    0.36
     प्रहरी
    0.36
    maja
    0.35
     Gson
    0.35
     심
    0.33
    迫
    0.33
     bump
    0.33
    キ
    0.33
     ragged
    0.32
    POSITIVE LOGITS
     മാര്‍
    0.38
    icast
    0.38
     COMPENSATION
    0.38
    绔
    0.36
    SHORT
    0.35
    替
    0.35
     علامت
    0.35
    แปลง
    0.35
    вяз
    0.35
    বেশ
    0.35
    Activations Density 0.000%

    No Known Activations