© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161101
    Prev
    Next
    INDEX
    Explanations

    Bao

    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_2_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
    in
    1.41
     інші
    1.11
    ことができる
    1.09
     generalizing
    1.07
     parameterized
    1.05
    矚
    1.05
     ถึง
    1.03
    inę
    1.03
    αν
    1.02
     oblik
    1.02
    POSITIVE LOGITS
    i
    1.96
    ي
    1.88
    ت
    1.59
    d
    1.58
    t
    1.55
    y
    1.45
     was
    1.41
    ד
    1.41
    י
    1.38
    n
    1.35
    Activations Density 0.000%

    No Known Activations