© 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. 7968
    Prev
    Next
    INDEX
    Explanations

    descriptive language, particularly those that convey strong emotions or physical sensations.

    oai_token-act-pair · gemini-2.0-flash

    Bodily sensations

    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
     الوا
    -0.49
     blur
    -0.48
    PageRoute
    -0.48
     Meksiku
    -0.47
     createState
    -0.47
    issait
    -0.47
    )++;
    -0.47
     atras
    -0.47
    ONSORED
    -0.47
    POSITIVE LOGITS
     er
    1.10
    Er
    0.69
     Er
    0.64
    ReusableCell
    0.63
    
    0.59
    SOUNDBITE
    0.59
    +#+#
    0.59
     للمعارف
    0.57
    <bos>
    0.54
     processi
    0.54
    Activations Density 4.635%

    No Known Activations