© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112756
    Prev
    Next
    INDEX
    Explanations

    past tense endings "ed"

    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_2_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
    رود
    1.01
    $}
    0.91
    いろんな
    0.91
    ϓ
    0.89
     말미암아
    0.89
    鐩
    0.88
    sendBuf
    0.86
    এছাড়া
    0.86
    offers
    0.85
    quadratic
    0.84
    POSITIVE LOGITS
    ed
    1.44
    ，
    1.36
    p
    1.34
    ным
    1.32
    ،
    1.30
    、
    1.27
    و
    1.20
    _
    1.19
    َ
    1.19
    та
    1.18
    Activations Density 0.000%

    No Known Activations