© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178518
    Prev
    Next
    INDEX
    Explanations

    not ... too/necessarily/overly

    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_24_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
    notify
    0.45
    together
    0.43
    secure
    0.43
    trim
    0.42
    関
    0.40
    visor
    0.40
    backpack
    0.39
     तभी
    0.39
    separ
    0.38
    select
    0.38
    POSITIVE LOGITS
     व्हायरल
    0.42
     dét
    0.38
     adına
    0.38
     (=
    0.38
     রাজধানী
    0.38
     ड
    0.38
     răz
    0.37
     Roads
    0.37
     COMPENSATION
    0.37
     Compensation
    0.37
    Activations Density 0.013%

    No Known Activations