Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6972
    Prev
    Next
    INDEX
    Explanations

    text where first person pronouns are in use

    oai_token-act-pair · gemini-2.0-flash

    express opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ########.
    -0.93
    expandindo
    -0.52
    ChildScrollView
    -0.50
     فريبيس
    -0.50
    AutoScaleMode
    -0.50
    WebServlet
    -0.47
     }}"></
    -0.46
     ModelExpression
    -0.45
     AssemblyTitle
    -0.45
    eclared
    -0.45
    POSITIVE LOGITS
     opinion
    1.42
     believe
    1.34
     believes
    1.27
     belief
    1.23
    opinion
    1.19
     think
    1.19
    believe
    1.19
     thinks
    1.17
     believed
    1.12
    belie
    1.12
    Activations Density 4.387%

    No Known Activations