© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52498
    Prev
    Next
    INDEX
    Explanations

    forming or constituting something

    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_30_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
     stimulates
    0.38
    悰
    0.38
     concession
    0.38
     mnogo
    0.37
     associating
    0.36
    ovce
    0.36
     rental
    0.35
     instantiation
    0.35
     Sponsored
    0.34
     waarbij
    0.34
    POSITIVE LOGITS
    的一部分
    0.39
     axis
    0.38
    的基础
    0.38
    íč
    0.36
     naš
    0.36
    軸
    0.35
     हाम
    0.35
    元素的
    0.35
    我們的
    0.34
    直
    0.34
    Activations Density 0.004%

    No Known Activations