© 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. 14874
    Prev
    Next
    INDEX
    Explanations

    words as "well", "able", some present participle verbs, conjunctions

    oai_token-act-pair · gemini-2.0-flash

    well

    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
    ########.
    -0.79
     <=",
    -0.77
    TagMode
    -0.75
    aarrggbb
    -0.71
    abestanden
    -0.69
     EClass
    -0.66
    fjspx
    -0.64
    DoubleQuotes
    -0.58
    脚注の使い方
    -0.56
    Diwedd
    -0.56
    POSITIVE LOGITS
    etheless
    0.65
     socializing
    0.63
     ſta
    0.63
     undertaking
    0.62
     conveying
    0.61
     sustaining
    0.60
     pleaſure
    0.60
     organizing
    0.60
     optimizing
    0.60
     generating
    0.59
    Activations Density 2.937%

    No Known Activations