© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4362
    Prev
    Next
    INDEX
    Explanations

    articles and words related to being a member of a group, an object, or a place

    oai_token-act-pair · gemini-2.0-flash

    Legal status

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Member
    -1.13
     member
    -1.10
     Members
    -1.09
    Member
    -1.07
    Members
    -1.06
     MEMBER
    -1.06
     members
    -1.01
    members
    -1.00
     MEMBERS
    -0.96
    MEMBER
    -0.95
    POSITIVE LOGITS
     Мексичка
    0.62
    GenerationType
    0.59
    parsedMessage
    0.58
    stateProvider
    0.57
    EndGlobalSection
    0.56
    verwijspagina
    0.55
    ברס
    0.55
     JpaRepository
    0.53
     aggiorn
    0.50
    vejte
    0.48
    Activations Density 6.435%

    No Known Activations