© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51720
    Prev
    Next
    INDEX
    Explanations

    provide positive or helpful

    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_31_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
     CEA
    0.43
    Whitespace
    0.40
    紹
    0.39
    躾
    0.38
    য়নে
    0.38
     objectivity
    0.38
     Robot
    0.38
     robot
    0.37
     Roboto
    0.37
     roaming
    0.37
    POSITIVE LOGITS
    warm
    0.37
    γ
    0.36
    ặt
    0.36
    ác
    0.35
    Assassin
    0.35
    箫
    0.35
    preco
    0.35
    찰
    0.35
    estados
    0.34
    ocles
    0.34
    Activations Density 0.010%

    No Known Activations