© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176994
    Prev
    Next
    INDEX
    Explanations

    keras model definition

    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_24_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
    ቅር
    0.41
    軾
    0.39
    数十
    0.39
    btw
    0.37
    銖
    0.37
    Lic
    0.37
    財
    0.37
    ども
    0.37
    したり
    0.36
    Ac
    0.35
    POSITIVE LOGITS
     passages
    0.48
     disciplined
    0.44
     glist
    0.44
     passage
    0.43
     hostname
    0.41
     universidad
    0.40
     airplanes
    0.40
     answered
    0.40
     passagem
    0.40
    %!
    0.40
    Activations Density 0.000%

    No Known Activations