© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13216
    Prev
    Next
    INDEX
    Explanations

    words or phrases that describe a dilemma and its consequences, especially in political and medical contexts.

    oai_token-act-pair · gemini-2.0-flash

    Medicine and signatures

    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
     sign
    -3.17
     signs
    -3.05
     Sign
    -2.97
     Signs
    -2.88
     SIGN
    -2.75
    Signs
    -2.70
    Sign
    -2.67
    signs
    -2.66
     signed
    -2.63
    sign
    -2.59
    POSITIVE LOGITS
     OMIT
    0.49
    BaseAdapter
    0.49
    ลิต
    0.48
    kulum
    0.47
    NewUrlParser
    0.46
    AudioSource
    0.44
     Shand
    0.42
    slideUp
    0.42
    mybatisplus
    0.42
     viaggi
    0.42
    Activations Density 2.344%

    No Known Activations