© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9055
    Prev
    Next
    INDEX
    Explanations

    passages where things are getting worse

    oai_token-act-pair · gemini-2.0-flash

    worse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     worse
    -2.47
    worse
    -2.11
     worst
    -2.09
     Worse
    -1.99
    Worse
    -1.86
     Worst
    -1.76
    worst
    -1.68
    Worst
    -1.66
     peggio
    -1.59
     peor
    -1.55
    POSITIVE LOGITS
     snippetHide
    0.59
     verwe
    0.57
    DataAnnotations
    0.55
    ExecuteReader
    0.51
    KURZBESCHREIBUNG
    0.51
    cepan
    0.50
    exitRule
    0.50
    tvguidetime
    0.50
    отно
    0.49
    XmlAccessType
    0.49
    Activations Density 0.949%

    No Known Activations