© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104351
    Prev
    Next
    INDEX
    Explanations

    starts sentences "It"

    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_1_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
    ating
    0.91
    )**
    0.90
     on
    0.90
    /)
    0.89
     In
    0.88
    $)
    0.88
    ने
    0.87
    Down
    0.86
     It
    0.85
    ).
    0.84
    POSITIVE LOGITS
     invités
    1.05
    m
    1.05
     город
    1.03
    ຜະລິດຕະພັນ
    1.03
    ຈັດສົ່ງ
    1.01
    ться
    0.99
    0
    0.98
    том
    0.98
    ປະກອບ
    0.97
     clés
    0.96
    Activations Density 0.010%

    No Known Activations