© 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. 112491
    Prev
    Next
    INDEX
    Explanations

    gameplay

    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
    ות
    2.23
    ים
    1.74
    ת
    1.74
    ס
    1.73
    ു
    1.48
    d
    1.44
    s
    1.42
    el
    1.36
    ,
    1.34
    רים
    1.32
    POSITIVE LOGITS
    O
    1.27
     añad
    1.22
    padă
    1.21
    的过程中
    1.15
    E
    1.13
    的名字
    1.12
    த்து
    1.10
    P
    1.09
    的基本
    1.06
     célébr
    1.06
    Activations Density 0.002%

    No Known Activations