© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50204
    Prev
    Next
    INDEX
    Explanations

    witch

    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_55_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
     want
    0.47
     muốn
    0.41
    [multimodal]
    0.41
     don
    0.40
     기반
    0.37
    ውነ
    0.37
    మ్ము
    0.37
    📆
    0.37
     quiere
    0.36
     vuoi
    0.36
    POSITIVE LOGITS
    des
    0.41
    annia
    0.38
    stan
    0.37
    unya
    0.35
     Ree
    0.34
    ліся
    0.34
    istaa
    0.34
     रामानंद
    0.33
     Des
    0.33
    iasco
    0.33
    Activations Density 0.022%

    No Known Activations