© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12098
    Prev
    Next
    INDEX
    Explanations

    words related to cooperation and sponsorship

    oai_token-act-pair · gemini-2.0-flash

    sponsorship

    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
     sponsor
    -2.52
     sponsors
    -2.36
     Sponsor
    -2.28
     sponsored
    -2.22
     sponsorship
    -2.22
     Sponsors
    -2.19
     sponsoring
    -2.17
    Sponsor
    -2.16
    Sponsors
    -2.03
     SPONS
    -2.02
    POSITIVE LOGITS
    complexContent
    0.60
    sp
    0.60
    Gotcha
    0.52
     Normdatei
    0.50
     emerg
    0.48
    LEncoder
    0.47
    findpost
    0.46
     createContext
    0.46
    ósito
    0.44
    GrantedAuthority
    0.44
    Activations Density 2.825%

    No Known Activations