© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66888
    Prev
    Next
    INDEX
    Explanations

    text

    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
     Há
    0.47
    ရာ
    0.43
    𝗈
    0.39
     mania
    0.39
    快樂
    0.38
    ulkar
    0.38
     होता
    0.37
    Mania
    0.37
     mould
    0.37
     라
    0.37
    POSITIVE LOGITS
     gran
    0.44
    য়নের
    0.41
    ņ
    0.41
    Allocation
    0.40
    elom
    0.39
    無線
    0.38
     granulation
    0.38
     persisted
    0.38
    秘密
    0.38
    imsy
    0.38
    Activations Density 0.001%

    No Known Activations