© 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. 58007
    Prev
    Next
    INDEX
    Explanations

    souvenirs

    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
    會
    1.42
    会
    1.41
    t
    1.36
    จะ
    1.27
    కు
    1.19
    и
    1.16
    و
    1.13
    ，
    1.12
    在
    1.05
    没有
    1.04
    POSITIVE LOGITS
     সরাস
    1.04
    רות
    1.00
    uhe
    0.98
    atas
    0.95
    brightness
    0.94
    ல்
    0.92
    us
    0.91
    purecounter
    0.89
    apes
    0.89
    ன்
    0.88
    Activations Density 0.000%

    No Known Activations