© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16253
    Prev
    Next
    INDEX
    Explanations

    language about personal experiences and feelings, especially those related to hardship or emotional change

    oai_token-act-pair · gemini-2.0-flash

    go

    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
     through
    -0.86
     समीक्षाओं
    -0.86
     createContext
    -0.83
    MemoryWarning
    -0.82
    Rujuakan
    -0.82
    Thru
    -0.82
     Through
    -0.77
    Through
    -0.76
    TagMode
    -0.71
    ValueStyle
    -0.70
    POSITIVE LOGITS
     go
    2.19
     goes
    2.11
     went
    1.91
    goes
    1.88
    go
    1.82
     going
    1.80
    Go
    1.77
     Go
    1.71
     gone
    1.70
    went
    1.70
    Activations Density 3.395%

    No Known Activations