© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81111
    Prev
    Next
    INDEX
    Explanations

    intramuscular injection or exposition structure

    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_0_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
    ak
    1.48
    ד
    1.48
    6
    1.47
    д
    1.45
     adecuado
    1.34
    0
    1.34
     conectado
    1.33
    いろんな
    1.33
     permitido
    1.30
    ש
    1.30
    POSITIVE LOGITS
     was
    1.48
    ка
    1.32
    ELL
    1.23
    on
    1.20
    was
    1.20
    .
    1.17
     be
    1.16
    ail
    1.14
    ds
    1.09
    ून
    1.06
    Activations Density 0.000%

    No Known Activations