© 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. 161569
    Prev
    Next
    INDEX
    Explanations

    doing this

    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
    のは
    1.03
    N
    0.98
     Dependencies
    0.83
    Tinh
    0.80
    ด
    0.79
    if
    0.77
    with
    0.77
    高い
    0.77
    >();
    0.77
    when
    0.77
    POSITIVE LOGITS
    )
    1.18
    ;
    1.16
    h
    1.13
    ]
    1.10
    n
    1.09
    ية
    1.07
    d
    1.05
    cı
    1.02
    ő
    1.02
    r
    1.00
    Activations Density 0.001%

    No Known Activations