© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9325
    Prev
    Next
    INDEX
    Explanations

    Bank of America, HSBC, ICICI Bank

    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
    æs
    0.16
    ués
    0.14
    <unused2117>
    0.14
     یہی
    0.14
    squiggle
    0.13
    業者
    0.13
    ’
    0.13
     সম্ভবনা
    0.13
    dDevice
    0.13
    
    0.13
    POSITIVE LOGITS
     kutoka
    0.16
    N
    0.16
     Halls
    0.15
     lie
    0.15
     لين
    0.15
     Pele
    0.15
     gathering
    0.14
     trouv
    0.14
     เก็บ
    0.14
     Banks
    0.14
    Activations Density 0.017%

    No Known Activations