© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90154
    Prev
    Next
    INDEX
    Explanations

    amplifies

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    i
    0.58
     sin
    0.43
    y
    0.42
    י
    0.42
    kinds
    0.41
     geom
    0.40
    iencia
    0.40
    ياب
    0.40
     bacter
    0.39
    Works
    0.39
    POSITIVE LOGITS
    ain
    1.33
    ainment
    0.57
    inued
    0.51
    ainan
    0.50
    AIN
    0.48
    ੳ
    0.43
     Alain
    0.42
    ہیں
    0.42
    aini
    0.41
     Wainwright
    0.41
    Activations Density 0.000%

    No Known Activations