© 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. 90305
    Prev
    Next
    INDEX
    Explanations

    carbon offset

    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
    omers
    0.66
    eln
    0.65
    AP
    0.64
     tempering
    0.64
    ’
    0.64
    us
    0.64
    jer
    0.61
    ists
    0.60
    ut
    0.58
    AS
    0.58
    POSITIVE LOGITS
    h
    0.89
    此
    0.64
     fluctuate
    0.62
    لي
    0.62
     esté
    0.62
     adimensional
    0.61
    تي
    0.60
     họ
    0.60
     azúcar
    0.60
    соеди
    0.59
    Activations Density 0.001%

    No Known Activations