© 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. 22557
    Prev
    Next
    INDEX
    Explanations

    word parts or technical terms

    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
    t
    0.51
    ument
    0.39
    supset
    0.38
    estrian
    0.38
    supseteq
    0.37
     practically
    0.35
    subset
    0.34
    睿
    0.34
    qq
    0.33
    ennie
    0.33
    POSITIVE LOGITS
    ць
    0.42
     Henning
    0.38
     nơi
    0.37
     accomod
    0.37
    几种
    0.36
    接过
    0.35
    omel
    0.35
     postup
    0.34
    పి
    0.34
    LException
    0.34
    Activations Density 0.032%

    No Known Activations