© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206108
    Prev
    Next
    INDEX
    Explanations

    inflating or filled balloons

    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_20_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
    ilización
    0.45
     ricerca
    0.44
    umball
    0.44
    砭
    0.44
    砧
    0.44
    事例
    0.42
     выборах
    0.42
    Research
    0.42
    砟
    0.42
     prenda
    0.42
    POSITIVE LOGITS
     sl
    0.54
    గాలు
    0.47
     cultured
    0.45
     j
    0.45
     extracted
    0.45
     encro
    0.44
     č
    0.44
     swoje
    0.42
     tache
    0.41
     black
    0.41
    Activations Density 0.000%

    No Known Activations