© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6892
    Prev
    Next
    INDEX
    Explanations

    email headers including date and time of sending.

    oai_token-act-pair · gemini-2.0-flash

    Code/email snippets

    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
     from
    -1.63
     with
    -1.54
     at
    -1.49
    from
    -1.40
    with
    -1.34
     by
    -1.33
     through
    -1.33
     as
    -1.30
     on
    -1.28
     before
    -1.27
    POSITIVE LOGITS
    oredCriteria
    0.58
    MessageTagHelper
    0.55
     mauvaises
    0.52
    parsedMessage
    0.49
     mooie
    0.48
    มัน
    0.48
     jullie
    0.47
     svå
    0.47
     questo
    0.47
     easiest
    0.47
    Activations Density 9.601%

    No Known Activations