© 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. 12305
    Prev
    Next
    INDEX
    Explanations

    words relating to the goals, actions, roles, and characteristics of people.

    oai_token-act-pair · gemini-2.0-flash

    Dedicated to something

    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
     helping
    -1.12
    Promoting
    -1.10
     promoting
    -1.07
    helping
    -1.07
    Helping
    -1.04
     enhancing
    -1.03
     Helping
    -1.02
     facilitating
    -1.01
     Promoting
    -1.00
     preventing
    -0.98
    POSITIVE LOGITS
     فريبيس
    0.62
    SequentialGroup
    0.52
    ArgsConstructor
    0.52
    Auszeichnungen
    0.48
    ,:)
    0.48
    XmlAccessType
    0.48
     bahawa
    0.46
     للمعارف
    0.45
    وروبا
    0.44
    CloseOperation
    0.44
    Activations Density 4.583%

    No Known Activations