© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3307
    Prev
    Next
    INDEX
    Explanations

    words related to business locations, especially the word "branch"

    oai_token-act-pair · gemini-2.0-flash

    business locations (branch, offices)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     CreateTagHelper
    -0.56
     Wiktionnaire
    -0.55
    estacks
    -0.55
    icity
    -0.54
    cius
    -0.53
    lasma
    -0.50
    jaro
    -0.50
     Signalez
    -0.50
    uxxxx
    -0.50
     komp
    -0.49
    POSITIVE LOGITS
     Branches
    0.76
     branch
    0.73
     branches
    0.73
    Branch
    0.71
     Branch
    0.70
    branches
    0.68
    branch
    0.67
     cabang
    0.66
     фили
    0.65
    ursales
    0.63
    Activations Density 0.632%

    No Known Activations