© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250019
    Prev
    Next
    INDEX
    Explanations

    **

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Few
    0.43
    DAT
    0.41
    '))
    0.41
    Email
    0.40
    Originally
    0.40
    "))
    0.39
    "
    0.39
    Currently
    0.39
    "}}
    0.39
    POSITIVE LOGITS
     following
    0.44
     (“
    0.43
     any
    0.39
     ona
    0.39
     nonetheless
    0.39
    是从
    0.39
     resulting
    0.38
     csak
    0.37
     demás
    0.37
     isOn
    0.37
    Activations Density 0.004%

    No Known Activations