© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232021
    Prev
    Next
    INDEX
    Explanations

    someone says or does

    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
    to
    1.00
    다
    0.97
    .
    0.94
     to
    0.85
    on
    0.84
    на
    0.80
     on
    0.80
    ले
    0.80
     model
    0.78
     line
    0.74
    POSITIVE LOGITS
    ী
    1.10
     cambia
    0.98
     bombarded
    0.97
     enfri
    0.96
     powied
    0.95
     pouquinho
    0.93
    મ
    0.93
     aument
    0.92
     добав
    0.92
     incluidas
    0.91
    Activations Density 0.004%

    No Known Activations