© 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. 5603
    Prev
    Next
    INDEX
    Explanations

    DHS

    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
     synergies
    0.40
     bellezza
    0.40
     Ж
    0.39
     bombas
    0.39
    Monica
    0.39
     congén
    0.38
     contempor
    0.38
     রহস্য
    0.37
    Сред
    0.37
     insp
    0.37
    POSITIVE LOGITS
    olateral
    0.43
     Humphreys
    0.38
    절
    0.37
    oader
    0.37
    oitte
    0.37
     éd
    0.36
    humid
    0.35
    خول
    0.35
    Pixel
    0.35
    ěj
    0.35
    Activations Density 0.000%

    No Known Activations