© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3284
    Prev
    Next
    INDEX
    Explanations

    sentences or clauses with multiple conjunctions strung together, especially when they involve second person pronouns "you" or "we".

    oai_token-act-pair · gemini-2.0-flash

    Planning and anticipation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    خته
    -0.48
    )?;
    -0.46
    ReusableCell
    -0.46
    ádza
    -0.46
    MessageTagHelper
    -0.45
     AssemblyTitle
    -0.44
    DriverManager
    -0.43
    godic
    -0.43
    Begriffsklä
    -0.43
    <?
    -0.42
    POSITIVE LOGITS
    Bibliograf
    0.63
    LookAnd
    0.62
     ride
    0.62
     count
    0.59
     planen
    0.58
     typelib
    0.58
    förs
    0.56
     riding
    0.56
     Riding
    0.55
    quirrels
    0.55
    Activations Density 2.303%

    No Known Activations