© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 110235
    Prev
    Next
    INDEX
    Explanations

    concatenation

    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
    1.35
    I
    1.32
    는
    1.32
    b
    1.30
    اً
    1.26
    ح
    1.22
    را
    1.20
    l
    1.20
    r
    1.18
    f
    1.16
    POSITIVE LOGITS
     for
    1.32
    1.28
     antiviral
    0.95
    те
    0.92
     കൂടുതൽ
    0.90
     generalizes
    0.89
     nuns
    0.87
     așa
    0.86
    ：
    0.86
    ত্বের
    0.86
    Activations Density 0.000%

    No Known Activations