© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237904
    Prev
    Next
    INDEX
    Explanations

    RNA and DNA comparisonRNA replicationRNA rolesRNA catalystsRNA virus

    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_32_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
     gamble
    0.37
     mRNAs
    0.37
    笙
    0.35
    Ordered
    0.35
    рованное
    0.34
    質の
    0.34
     ሂ
    0.33
     ആരോപ
    0.33
     +"
    0.33
    行き
    0.33
    POSITIVE LOGITS
     replaced
    0.42
     reempl
    0.41
     replacing
    0.40
     Naj
    0.38
    獷
    0.38
     aproxim
    0.38
    Replace
    0.38
     sostitu
    0.38
    replaced
    0.38
     शेवट
    0.38
    Activations Density 0.002%

    No Known Activations