© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52753
    Prev
    Next
    INDEX
    Explanations

    I was [feeling/state]

    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_31_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
     pén
    0.37
    破解
    0.35
    努力
    0.35
    පු
    0.33
    Пер
    0.32
    yship
    0.32
    손
    0.32
    nyj
    0.32
     निधी
    0.32
    두
    0.32
    POSITIVE LOGITS
     decades
    0.42
     carelessly
    0.38
     Helens
    0.37
    áciu
    0.36
    ValueSet
    0.35
     deplete
    0.35
     capric
    0.35
     doubting
    0.34
     contesting
    0.34
     கொண்டாட
    0.33
    Activations Density 0.002%

    No Known Activations