© 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. 112663
    Prev
    Next
    INDEX
    Explanations

    сборка, сборник

    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
    ل
    1.34
    t
    1.28
    י
    1.27
    i
    1.27
    :
    1.21
    ي
    1.21
    ّه
    1.19
    َ
    1.18
     an
    1.14
    н
    1.14
    POSITIVE LOGITS
    .
    1.61
    2
    1.47
    .}$
    1.27
    .。
    1.20
    .\"
    1.13
    4
    1.13
    .\\
    1.12
    time
    1.05
    ension
    1.05
    .`
    1.00
    Activations Density 0.001%

    No Known Activations