© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35534
    Prev
    Next
    INDEX
    Explanations

    alleviate poverty, water, reducing

    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_31_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
     सीएम
    0.42
    agin
    0.41
    otherArgs
    0.38
    <0x8A>
    0.37
    arg
    0.37
    ્યો
    0.37
    olome
    0.36
    〃
    0.36
     河
    0.36
    ADIAN
    0.36
    POSITIVE LOGITS
     பளி
    0.39
    ಿಯಾಗ
    0.37
    鏤
    0.37
    ማ
    0.36
     آئینہ
    0.36
    gef
    0.35
    लीफ
    0.35
     phép
    0.34
    として
    0.34
     ভার্চ
    0.33
    Activations Density 0.014%

    No Known Activations