© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43370
    Prev
    Next
    INDEX
    Explanations

    praying for others

    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_13_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
    یر
    0.70
    ের
    0.63
    와의
    0.63
    Verlag
    0.62
    AGON
    0.62
    τα
    0.61
     possam
    0.61
    ۹
    0.60
    спубли
    0.59
    Historically
    0.59
    POSITIVE LOGITS
     pets
    0.73
    pping
    0.61
     App
    0.61
     Eve
    0.59
    eto
    0.58
    prise
    0.58
     olymp
    0.58
    birds
    0.56
     eyeing
    0.56
    pring
    0.55
    Activations Density 0.000%

    No Known Activations