© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2519
    Prev
    Next
    INDEX
    Explanations

    xpath selectors

    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_38_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
    uple
    0.48
     [#
    0.43
    ]::
    0.41
    ;#
    0.39
     മത്സ്യ
    0.39
    ::$
    0.39
    ນິກ
    0.38
    oplevel
    0.38
    খাল
    0.37
    ষধ
    0.37
    POSITIVE LOGITS
    POSITORY
    0.38
     Khartoum
    0.37
     इमो
    0.36
     Kho
    0.36
     للك
    0.36
     aud
    0.36
    限
    0.36
     inmun
    0.35
     embal
    0.35
    किंग
    0.35
    Activations Density 0.005%

    No Known Activations