© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180833
    Prev
    Next
    INDEX
    Explanations

    use markdown list formatting

    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_29_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
    সুমে
    0.39
     If
    0.38
    鱗
    0.37
    緒
    0.36
    スケ
    0.35
     Gemeins
    0.34
     prévention
    0.34
     Dunes
    0.34
     Medication
    0.33
     Recommended
    0.33
    POSITIVE LOGITS
    딜
    0.39
     sniper
    0.38
    ENSOR
    0.37
     debugger
    0.37
     whoever
    0.37
    removeAttr
    0.36
     charged
    0.36
     dealer
    0.36
    charged
    0.35
    голо
    0.35
    Activations Density 0.004%

    No Known Activations