© 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. 14868
    Prev
    Next
    INDEX
    Explanations

    words relating to giving advice, particularly using the words "you" and "to"

    oai_token-act-pair · gemini-2.0-flash

    online advertisements

    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
     (
    -0.63
    twimg
    -0.54
    <bos>
    -0.54
    conio
    -0.53
    ("/:
    -0.50
     Linkage
    -0.48
     Marine
    -0.48
    Marine
    -0.47
     fascic
    -0.47
    heen
    -0.45
    POSITIVE LOGITS
    RTDA
    0.62
    NewUrlParser
    0.62
    fjspx
    0.59
     convertView
    0.58
    isContained
    0.56
    igshid
    0.56
    orkin
    0.54
    ländische
    0.52
     виправивши
    0.50
    PyExc
    0.49
    Activations Density 12.171%

    No Known Activations