© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11636
    Prev
    Next
    INDEX
    Explanations

    the words "so", "as", "this", "thus", and "far"

    oai_token-act-pair · gemini-2.0-flash

    the concept of distance

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

    far

    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
    }));
    -0.48
     RouterModule
    -0.41
    }))
    -0.41
    HasIndex
    -0.40
     thofe
    -0.39
    PropertyChanging
    -0.38
    Santo
    -0.38
    ̍t
    -0.38
    audiovisuel
    -0.38
     sababu
    -0.38
    POSITIVE LOGITS
     far
    3.55
    far
    2.73
    Far
    2.45
     Far
    2.31
     FAR
    2.22
    FAR
    1.97
     jauh
    1.89
     langt
    1.86
     lejos
    1.66
     daleko
    1.65
    Activations Density 1.357%

    No Known Activations