© 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. 112737
    Prev
    Next
    INDEX
    Explanations

    nhạc

    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
    も
    1.64
    א
    1.45
     in
    1.43
    ও
    1.41
    도
    1.40
    ח
    1.38
    אן
    1.30
    צ
    1.20
    いた
    1.16
    ד
    1.15
    POSITIVE LOGITS
    ного
    1.48
    as
    1.32
    し
    1.27
    <0x0D>
    1.05
    ться
    1.04
     asesin
    1.03
    ї
    1.02
    iciency
    1.01
    an
    1.00
    sthe
    1.00
    Activations Density 0.000%

    No Known Activations