© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14819
    Prev
    Next
    INDEX
    Explanations

    return or back

    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_34_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
     cellpadding
    0.41
     கல்ல
    0.38
     hollow
    0.37
    coa
    0.36
     thay
    0.34
    淩
    0.34
     defenses
    0.34
     टेन
    0.34
     rufo
    0.34
     ವಾ
    0.34
    POSITIVE LOGITS
    戻
    1.68
     वापस
    1.66
    に戻
    1.64
     возвра
    1.57
     tillbaka
    1.55
     return
    1.55
     вернуться
    1.55
     zurück
    1.54
    回到
    1.54
     terug
    1.52
    Activations Density 0.061%

    No Known Activations