© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159895
    Prev
    Next
    INDEX
    Explanations

    name, program, variables, intelligence, law

    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
     are
    2.17
    o
    1.20
    do
    1.20
    lerine
    1.17
     isomorphic
    1.13
    नं
    1.09
    न
    1.08
    soever
    1.07
    nge
    1.07
     can
    1.05
    POSITIVE LOGITS
    И
    1.51
    在
    1.41
    會
    1.39
    In
    1.37
    ில்
    1.31
    I
    1.31
    أ
    1.30
    一
    1.27
    ل
    1.25
    آ
    1.23
    Activations Density 0.001%

    No Known Activations