© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46184
    Prev
    Next
    INDEX
    Explanations

    joining

    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_10_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
    ]。
    0.45
    RI
    0.45
    h
    0.42
    墘
    0.41
    )。
    0.39
     weg
    0.39
    烜
    0.39
    一個
    0.38
     zdrav
    0.38
    রীণ
    0.38
    POSITIVE LOGITS
    the
    0.57
    었다
    0.53
    ate
    0.49
    ust
    0.48
    ation
    0.48
    nya
    0.47
    joining
    0.47
    ot
    0.45
    raient
    0.45
    ra
    0.44
    Activations Density 0.004%

    No Known Activations