© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167611
    Prev
    Next
    INDEX
    Explanations

    eBay

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    NCIA
    0.40
    Incrementor
    0.38
    retryWrites
    0.37
    ስ
    0.37
     Consid
    0.37
     marketplace
    0.37
     Ví
    0.36
    要知道
    0.36
    stun
    0.36
     disponíveis
    0.36
    POSITIVE LOGITS
     specialised
    0.42
     speciality
    0.41
    */
    0.38
     specialise
    0.38
     unfavourable
    0.38
     specialises
    0.37
     code
    0.37
    作品
    0.36
    motif
    0.36
     proper
    0.36
    Activations Density 0.002%

    No Known Activations