© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44541
    Prev
    Next
    INDEX
    Explanations

    names/endings with 'aj', 'ra', 'ia', 'era'

    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
    0.77
    na
    0.73
    m
    0.71
    ér
    0.69
    ssä
    0.65
    يل
    0.64
    stm
    0.64
    ste
    0.63
     flashes
    0.62
    ют
    0.61
    POSITIVE LOGITS
    ת
    1.02
    י
    1.01
    い
    0.96
    i
    0.84
    ו
    0.84
    ി
    0.83
    I
    0.78
    ي
    0.78
     می
    0.76
    و
    0.76
    Activations Density 0.003%

    No Known Activations