© 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. 135122
    Prev
    Next
    INDEX
    Explanations

    loud noises

    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
    ו
    1.13
     o
    1.02
     exorbitant
    0.99
     orbital
    0.90
     organisations
    0.89
    
    0.89
     organizations
    0.88
     scepticism
    0.88
    ין
    0.86
     defraud
    0.86
    POSITIVE LOGITS
    v
    1.58
    b
    1.54
    f
    1.47
    m
    1.30
    n
    1.13
    d
    1.13
    p
    1.13
    j
    1.11
    C
    0.98
    h
    0.97
    Activations Density 0.001%

    No Known Activations