© 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. 43049
    Prev
    Next
    INDEX
    Explanations

    Salesforce CRM

    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
    ऑन
    0.54
    ံ့
    0.54
    िले
    0.51
    郄
    0.50
     fortsatt
    0.49
     rotting
    0.47
     Chứng
    0.46
    Arkansas
    0.46
    ToCheck
    0.46
    പ്പിക്ക
    0.46
    POSITIVE LOGITS
     referencia
    0.52
    blätter
    0.50
     લ
    0.49
    ]),
    0.49
    𝗍
    0.48
     Cesar
    0.46
    gist
    0.45
    沙漠
    0.45
     reminiscent
    0.45
     ચંદ્ર
    0.45
    Activations Density 0.045%

    No Known Activations