© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86069
    Prev
    Next
    INDEX
    Explanations

    `ngOnInit` or `onMounted` calls

    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_18_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
     котором
    0.56
     crossbow
    0.54
     springfox
    0.53
    UEL
    0.51
     vanwege
    0.50
     autrefois
    0.48
    鐲
    0.48
     Wochschr
    0.48
     소개
    0.47
    UILLER
    0.47
    POSITIVE LOGITS
    line
    0.58
    life
    0.56
    lines
    0.54
    ring
    0.52
    Ნ
    0.49
    reel
    0.48
    row
    0.47
    well
    0.47
    time
    0.47
     participating
    0.47
    Activations Density 0.000%

    No Known Activations