© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44311
    Prev
    Next
    INDEX
    Explanations

    investment accounts

    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_22_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
    ㎥
    0.41
     обслуживания
    0.38
     {\
    0.38
     क्लब
    0.38
     आरंभ
    0.38
     chrét
    0.38
     badań
    0.37
     venue
    0.36
     kwietnia
    0.36
     τρί
    0.36
    POSITIVE LOGITS
    conserv
    0.45
     conserv
    0.44
     Conserv
    0.44
    cec
    0.44
    Ⲩ
    0.44
     Yhat
    0.43
    Conserv
    0.42
    هد
    0.41
    දහ
    0.41
     hypersur
    0.40
    Activations Density 0.002%

    No Known Activations