© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52075
    Prev
    Next
    INDEX
    Explanations

    hey [speaker]

    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_31_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
    Please
    0.41
    Either
    0.38
    Ple
    0.37
    本当
    0.36
    Always
    0.36
    朗
    0.36
     Maintenant
    0.36
    PLEASE
    0.35
     хочется
    0.35
    🙏
    0.35
    POSITIVE LOGITS
     resolve
    0.39
    oderm
    0.36
     πέ
    0.36
     успе
    0.35
     discounted
    0.35
    fore
    0.35
     sacer
    0.34
     issuers
    0.34
     तिलक
    0.34
     Stern
    0.34
    Activations Density 0.004%

    No Known Activations