© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140246
    Prev
    Next
    INDEX
    Explanations

    draw

    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_46_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
     RING
    0.48
     ringing
    0.44
     rings
    0.43
     रिंग
    0.43
    ଢ
    0.42
     ring
    0.41
     Ring
    0.41
     Rings
    0.39
    yside
    0.39
    니어
    0.38
    POSITIVE LOGITS
    thati
    0.40
    corpus
    0.38
    有一
    0.37
    deo
    0.36
     SMC
    0.36
     DeL
    0.36
    line
    0.35
    ills
    0.35
    asets
    0.35
    <?
    0.35
    Activations Density 0.001%

    No Known Activations