© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5030
    Prev
    Next
    INDEX
    Explanations

    shipping information from amazon

    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_39_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
     contradicts
    0.42
    पीएस
    0.38
     فارسی
    0.38
    potato
    0.38
     Advances
    0.37
    단체
    0.36
     cinese
    0.36
    㪯
    0.36
    ásico
    0.36
     중국
    0.36
    POSITIVE LOGITS
    Ι
    0.46
     Stor
    0.42
    早
    0.42
    inde
    0.40
     C
    0.39
    Good
    0.39
    இந்த
    0.38
     మంచి
    0.38
     Zas
    0.38
    grave
    0.38
    Activations Density 0.001%

    No Known Activations