© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250295
    Prev
    Next
    INDEX
    Explanations

    negations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    <0xE2>
    0.63
    ‎
    0.50
     ‘
    0.46
    ·
    0.46
    ……
    0.44
    …………
    0.44
     ……
    0.44
     ……………………
    0.43
    ​)
    0.43
    
    0.43
    POSITIVE LOGITS
     didnt
    2.17
     doesnt
    2.17
     youre
    2.17
     wasnt
    2.17
     couldnt
    2.09
     wouldnt
    2.09
     dont
    2.08
     isnt
    2.05
     theyre
    2.05
     arent
    2.05
    Activations Density 0.001%

    No Known Activations