© 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. 40965
    Prev
    Next
    INDEX
    Explanations

    suicide or dates

    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
     científicos
    0.68
     чемпиона
    0.67
     и
    0.64
     фильма
    0.64
    ٨
    0.61
     ácidos
    0.59
    ၆
    0.59
     раздел
    0.58
     و
    0.57
     доба
    0.57
    POSITIVE LOGITS
    is
    1.15
    j
    1.06
    ר
    1.05
    l
    0.96
    t
    0.95
    ل
    0.95
    n
    0.88
    p
    0.86
    h
    0.85
    r
    0.84
    Activations Density 0.005%

    No Known Activations