© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195667
    Prev
    Next
    INDEX
    Explanations

    New Year's Eve Countdown

    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_15_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
    typing
    0.48
    '!
    0.48
    ნიშვნელ
    0.47
    ੍
    0.47
    structured
    0.47
    Kont
    0.46
     Konstant
    0.46
    ції
    0.46
    ']);
    0.45
    τέ
    0.45
    POSITIVE LOGITS
     கல்லறை
    0.59
    er
    0.57
     atend
    0.57
     cao
    0.56
     reconst
    0.56
     L
    0.55
     cau
    0.54
     reconstru
    0.53
    &=\
    0.52
     capa
    0.52
    Activations Density 0.000%

    No Known Activations