© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 134
    Prev
    Next
    INDEX
    Explanations

    contexts using formal language describing agreements or processes

    oai_token-act-pair · gemini-2.0-flash

    say "into"

    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
     Into
    -1.53
    Into
    -1.43
     INTO
    -1.40
    into
    -1.34
    INTO
    -1.25
     to
    -1.15
    to
    -1.09
     into
    -1.03
     onto
    -0.86
    nto
    -0.84
    POSITIVE LOGITS
    MigrationBuilder
    1.00
    AddTagHelper
    0.95
     kasarigan
    0.89
     CreateTagHelper
    0.89
    +#+
    0.82
     beginnetje
    0.78
    NameInMap
    0.77
    rungsseite
    0.77
     AssemblyCompany
    0.76
    StoreMessageInfo
    0.75
    Activations Density 0.969%

    No Known Activations