© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92952
    Prev
    Next
    INDEX
    Explanations

    swift variable declarations

    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_11_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
    7
    0.40
    4
    0.40
    3
    0.38
    0.37
    -
    0.37
    9
    0.36
    ני
    0.36
    6
    0.35
     that
    0.35
    <
    0.35
    POSITIVE LOGITS
    𝕋
    0.33
     bijective
    0.32
    hete
    0.32
     perfused
    0.32
    鋃
    0.32
     reseñas
    0.31
     ventilated
    0.31
    ቄ
    0.30
    𒁲
    0.30
     courtroom
    0.30
    Activations Density 0.009%

    No Known Activations