© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66167
    Prev
    Next
    INDEX
    Explanations

    Al/Ali/All

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     végétale
    0.39
    스크
    0.39
    চন
    0.37
    ミラ
    0.37
    汙
    0.37
    ստ
    0.37
     دوسرا
    0.37
     vanilla
    0.36
     ሽ
    0.36
    evt
    0.36
    POSITIVE LOGITS
    agas
    0.48
    మన
    0.41
    ман
    0.40
     Lindsay
    0.39
    笠
    0.39
     проте
    0.38
     discontinue
    0.37
     Manchester
    0.37
    lym
    0.37
    다운
    0.37
    Activations Density 0.003%

    No Known Activations