© 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. 45922
    Prev
    Next
    INDEX
    Explanations

    mid-week travel or day slump

    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
    Z
    0.82
    R
    0.82
    ש
    0.72
    S
    0.71
    س
    0.71
    K
    0.69
    Size
    0.69
     Puppy
    0.68
    L
    0.68
    E
    0.67
    POSITIVE LOGITS
    اں
    0.68
    uje
    0.68
    casted
    0.68
    顕
    0.63
    য়া
    0.60
     هڪ
    0.60
    é
    0.59
    età
    0.58
     المللی
    0.58
    与
    0.57
    Activations Density 0.013%

    No Known Activations