© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240224
    Prev
    Next
    INDEX
    Explanations

    know what you want

    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_25_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
     Aguilar
    0.38
     Tzu
    0.36
    antuan
    0.35
    Coastal
    0.35
    𝙶
    0.34
    য়েছে
    0.34
    Semit
    0.34
     Realtors
    0.34
    ISING
    0.33
    ieszcz
    0.33
    POSITIVE LOGITS
    總
    0.45
     totaal
    0.41
    𝟎
    0.40
    ﺶ
    0.40
     Number
    0.39
     empires
    0.39
    congestion
    0.39
    력
    0.39
     வைத்து
    0.38
    氀
    0.38
    Activations Density 0.002%

    No Known Activations