© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57524
    Prev
    Next
    INDEX
    Explanations

    hours of credit

    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_11_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
     palace
    0.60
    $.
    0.59
    łą
    0.58
    Because
    0.55
     sanctuaries
    0.53
    Cars
    0.52
    érale
    0.50
    Slash
    0.50
    薨
    0.50
    ,:
    0.50
    POSITIVE LOGITS
     toda
    0.54
     (?)
    0.54
     подума
    0.54
     dSample
    0.52
    А
    0.52
     melanin
    0.50
     impenetr
    0.50
    釹
    0.50
    QUEST
    0.49
    ВИ
    0.49
    Activations Density 0.016%

    No Known Activations