© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153935
    Prev
    Next
    INDEX
    Explanations

    many

    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_60_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
    n
    0.81
    x
    0.58
    tr
    0.55
    k
    0.51
    w
    0.47
    తం
    0.41
    ts
    0.40
    几
    0.40
    trs
    0.40
    iest
    0.39
    POSITIVE LOGITS
     many
    2.19
    many
    1.91
     muitas
    1.80
     Many
    1.78
     многие
    1.76
     многих
    1.75
    Many
    1.70
     muitos
    1.70
     MANY
    1.69
     muchas
    1.68
    Activations Density 0.001%

    No Known Activations