© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21110
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ss
    1.67
    SS
    1.41
    ｓ
    1.32
    sss
    1.31
    س
    1.29
    𝐬
    1.27
    ѕ
    1.27
    ssss
    1.24
    Ss
    1.24
    𝚜
    1.24
    POSITIVE LOGITS
    ឥត
    0.35
    તમાં
    0.35
     diverge
    0.34
    derdag
    0.34
     Lank
    0.34
    ;%%
    0.34
    ীদার
    0.34
    क्कर
    0.33
    ག
    0.33
    ющим
    0.33
    Activations Density 0.071%

    No Known Activations