© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10292
    Prev
    Next
    INDEX
    Explanations

    negative statements indicated by "not", "no", and closely related language, as well as present-tense linking verbs and related words such as "mandatory", "optional", etc

    oai_token-act-pair · gemini-2.0-flash

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     незавершена
    -0.73
    Datuak
    -0.65
    Tracce
    -0.63
    ագրություններ
    -0.63
     estimés
    -0.61
    Much
    -0.60
    hyrchwyd
    -0.60
     Much
    -0.58
    InjectAttribute
    -0.58
    OGND
    -0.58
    POSITIVE LOGITS
    клопе
    0.54
     irreparable
    0.53
     counted
    0.53
    Rujuakan
    0.52
    ьаж
    0.52
    iastes
    0.51
     especially
    0.48
     environmentally
    0.47
    GRect
    0.47
    klär
    0.47
    Activations Density 4.292%

    No Known Activations