© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34296
    Prev
    Next
    INDEX
    Explanations

    emojis and specific characters

    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_7_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
     pavattati
    0.27
     manuss
    0.27
     sayıda
    0.25
     wygl
    0.25
    䍧
    0.25
    acional
    0.25
     اکاؤن
    0.24
     caract
    0.24
     cupcakes
    0.24
     आवंट
    0.24
    POSITIVE LOGITS
    на
    0.54
    ين
    0.43
    as
    0.43
    л
    0.43
     will
    0.42
    u
    0.41
    的
    0.41
    اً
    0.41
    on
    0.41
    é
    0.39
    Activations Density 0.001%

    No Known Activations