© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7204
    Prev
    Next
    INDEX
    Explanations

    PreviewProvider struct

    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_39_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
     eich
    0.44
    㓦
    0.42
    洎
    0.39
    Pepper
    0.37
    褙
    0.36
    ಿತಿ
    0.35
     lounges
    0.35
     बीटल
    0.35
    твра
    0.35
    itumor
    0.35
    POSITIVE LOGITS
    Enter
    0.40
     Enter
    0.40
    PLC
    0.38
     PLE
    0.36
     ort
    0.35
     PLC
    0.35
    涅
    0.35
     fruitful
    0.34
    askin
    0.34
    木
    0.34
    Activations Density 0.001%

    No Known Activations