© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59980
    Prev
    Next
    INDEX
    Explanations

    deposed, suppressed, subdued

    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_11_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
     procura
    0.61
     carer
    0.54
     chce
    0.53
    вард
    0.53
     busc
    0.52
    맛집
    0.52
     clic
    0.50
    燗
    0.50
     egress
    0.49
     hygiene
    0.49
    POSITIVE LOGITS
     এছাড়াও
    0.57
    Foreign
    0.54
    r
    0.53
    Languages
    0.52
    Bonus
    0.52
     Caution
    0.52
    Host
    0.51
    Citizens
    0.50
    Caution
    0.50
    Religious
    0.49
    Activations Density 0.006%

    No Known Activations