© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12290
    Prev
    Next
    INDEX
    Explanations

    years in the late 90s

    oai_token-act-pair · gemini-2.0-flash

    9

    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
    DataContract
    -0.51
     Efq
    -0.51
     مشين
    -0.48
    AutoScaleMode
    -0.48
     Lyd
    -0.45
     Taktlose
    -0.44
     BoxFit
    -0.43
    styleUrls
    -0.43
     صوتيه
    -0.43
    reactstrap
    -0.43
    POSITIVE LOGITS
    9
    0.77
    8
    0.59
    JE
    0.58
    7
    0.58
    ⁸
    0.56
    ⁹
    0.55
    ็จ
    0.51
     Ninety
    0.51
    出版年
    0.51
    ouncements
    0.50
    Activations Density 5.971%

    No Known Activations