© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230330
    Prev
    Next
    INDEX
    Explanations

    extreme damage

    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_6_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
    很
    1.00
     होता
    0.86
     changement
    0.84
    י
    0.83
    ]，
    0.81
    पणे
    0.80
    出门
    0.80
     saída
    0.76
    сным
    0.75
     ballpark
    0.72
    POSITIVE LOGITS
    o
    1.37
    os
    1.21
    ai
    1.16
    ing
    1.13
    og
    1.12
    ou
    1.11
    ul
    1.08
    es
    1.05
    員の
    1.03
    A
    1.01
    Activations Density 0.000%

    No Known Activations