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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 148145
    Prev
    Next
    INDEX
    Explanations

    housing size and type

    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_18_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
    цова
    0.46
    يدة
    0.46
    ণু
    0.43
    包
    0.42
    스로
    0.42
    激安
    0.41
     vattum
    0.41
     shops
    0.41
    ⇀
    0.41
     منہ
    0.40
    POSITIVE LOGITS
    anzia
    0.51
     Coastal
    0.48
    jenigen
    0.42
     Timber
    0.42
     Graham
    0.42
     propagated
    0.41
    arca
    0.41
     некоторых
    0.41
     according
    0.41
     சில
    0.41
    Activations Density 0.006%

    No Known Activations