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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12778
    Prev
    Next
    INDEX
    Explanations

    clauses using the pronoun "it" and modal verbs such as "would" or negative words such as "not."

    oai_token-act-pair · gemini-2.0-flash

    tokens with a focus on 'it' and related phrases

    np_token-act-pair-logits · gpt-4o-mini

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     femininas
    -0.49
     Its
    -0.49
    agisse
    -0.48
    defaultProps
    -0.46
     jovens
    -0.46
     its
    -0.44
     Leurs
    -0.44
     konkur
    -0.44
     suoi
    -0.44
    })*/
    -0.43
    POSITIVE LOGITS
     محفوظة
    0.74
     lenker
    0.68
    AsUp
    0.62
     оригіналу
    0.60
     defaultstate
    0.60
     ProtoMessage
    0.60
    DrawerToggle
    0.59
     مشين
    0.57
    tagHelper
    0.56
    новниш
    0.56
    Activations Density 0.444%

    No Known Activations