© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49272
    Prev
    Next
    INDEX
    Explanations

    Islamic

    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_55_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
    odil
    0.41
     органы
    0.40
     இந்திய
    0.37
    ji
    0.36
     ARISING
    0.35
    rose
    0.35
     কথিত
    0.35
    ձ
    0.34
    obil
    0.34
    বিদেশ
    0.34
    POSITIVE LOGITS
     thoughtful
    0.44
     Republic
    0.41
     biome
    0.40
    \"]\
    0.40
    erler
    0.39
     oriented
    0.39
     покрытия
    0.38
     personable
    0.37
     affective
    0.37
    ্বল
    0.36
    Activations Density 0.001%

    No Known Activations