© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60856
    Prev
    Next
    INDEX
    Explanations

    oppositeley

    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
    s
    1.49
    r
    1.35
     I
    1.20
     as
    1.19
     obie
    1.18
    ни
    1.17
    n
    1.14
    𝟎
    1.14
     contrat
    1.13
    ၀၀
    1.09
    POSITIVE LOGITS
    า
    1.34
    ↵
    1.26
    N
    1.01
    ]
    0.95
    아
    0.94
    izes
    0.93
    ugen
    0.92
    이나
    0.90
    enciado
    0.89
    ad
    0.89
    Activations Density 0.000%

    No Known Activations