© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203509
    Prev
    Next
    INDEX
    Explanations

    scientific plant names

    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_25_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
     have
    0.42
     ....
    0.39
     Realt
    0.39
     Santana
    0.38
    `,
    0.38
    iv
    0.38
    ).
    0.37
    ickeys
    0.37
    \)
    0.36
    ),
    0.36
    POSITIVE LOGITS
    交换
    0.48
     வால்பேப்பர்கள்
    0.44
    ंपूर्
    0.43
    钱包
    0.42
    沓
    0.42
    滗
    0.41
    瓈
    0.41
    পরিচিত
    0.41
     заработной
    0.40
    Notebook
    0.40
    Activations Density 0.001%

    No Known Activations