© 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. 8900
    Prev
    Next
    INDEX
    Explanations

    words related to a grievance, action taken, exhibit, and pictures, with a mix of verbs and nouns that relate to these subjects

    oai_token-act-pair · gemini-2.0-flash

    Actions taken

    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
     taking
    -2.34
    Taking
    -2.31
     Taking
    -2.28
    taking
    -2.27
    take
    -2.11
     take
    -2.08
     Take
    -2.03
     takes
    -2.03
    Take
    -2.03
     took
    -1.99
    POSITIVE LOGITS
     مشين
    0.57
    +#+#
    0.57
     ChromeDriver
    0.53
    tagHelperRunner
    0.53
    Rüyada
    0.52
    saraba
    0.52
    Varint
    0.48
    ChildIndex
    0.47
     CanadaChoose
    0.46
    ipro
    0.46
    Activations Density 3.023%

    No Known Activations