© 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. 41365
    Prev
    Next
    INDEX
    Explanations

    kaolin, kotlin, kali linux

    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
     with
    0.88
    t
    0.84
     swayed
    0.79
     as
    0.77
     wallet
    0.74
     are
    0.73
    -
    0.73
    tä
    0.72
     were
    0.70
    
    0.70
    POSITIVE LOGITS
    ort
    0.70
    ure
    0.69
    aste
    0.69
    ue
    0.67
    ens
    0.64
    ette
    0.64
    itting
    0.64
    old
    0.64
    ampa
    0.64
    ett
    0.63
    Activations Density 0.000%

    No Known Activations