© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5408
    Prev
    Next
    INDEX
    Explanations

    phrases that contain "gain" or "gaining" followed by words related to trend or popularity

    oai_token-act-pair · gemini-2.0-flash

    Gaining momentum/acceptance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    EndContext
    -0.76
    oa̍t
    -0.68
    ніципа
    -0.65
    CAPTION
    -0.63
    \}\\
    -0.63
    LookAnd
    -0.63
     censiti
    -0.62
    TestBed
    -0.62
     <",
    -0.62
     متعلقه
    -0.61
    POSITIVE LOGITS
    toEqual
    0.46
    BarStyle
    0.40
    brenner
    0.39
     terre
    0.37
     pace
    0.36
    func
    0.35
    ire
    0.35
    riak
    0.35
    лите
    0.35
    likan
    0.35
    Activations Density 1.122%

    No Known Activations