© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164348
    Prev
    Next
    INDEX
    Explanations

    backup

    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_13_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
    Eth
    0.48
    Vacc
    0.46
    iker
    0.46
    राबरी
    0.46
     /=
    0.45
    داء
    0.45
    operational
    0.44
    Ant
    0.44
     rôle
    0.44
    Toolkit
    0.44
    POSITIVE LOGITS
    명을
    0.50
     posibilidades
    0.49
     בפ
    0.48
    蟬
    0.48
     гипсо
    0.48
     Walling
    0.47
     पश्चिम
    0.47
     septembre
    0.46
     द्वार
    0.46
     beans
    0.46
    Activations Density 0.004%

    No Known Activations