© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127426
    Prev
    Next
    INDEX
    Explanations

    bombardment

    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_3_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
    с
    0.86
    ล
    0.73
    п
    0.63
    gif
    0.60
    gamma
    0.60
    ।.
    0.59
    ます
    0.57
    ྥ
    0.57
     on
    0.56
    ג
    0.55
    POSITIVE LOGITS
    _
    1.13
    and
    0.84
    +
    0.75
                    
    0.72
                 
    0.70
                
    0.68
                  
    0.67
    ur
    0.67
    '
    0.67
    లో
    0.65
    Activations Density 0.000%

    No Known Activations