© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1590
    Prev
    Next
    INDEX
    Explanations

    the letter h

    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_44_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
    污
    0.39
     cum
    0.38
     Gabri
    0.38
     soluble
    0.38
     indel
    0.37
    论
    0.37
    ника
    0.37
    лт
    0.37
     brach
    0.37
     otp
    0.36
    POSITIVE LOGITS
    ༣
    0.42
    ２
    0.41
    ₃
    0.40
    mero
    0.40
    3
    0.40
    २
    0.40
    ジア
    0.39
    转型
    0.39
    ３
    0.38
    III
    0.38
    Activations Density 0.018%

    No Known Activations