© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13240
    Prev
    Next
    INDEX
    Explanations

    plural nouns

    oai_token-act-pair · gemini-2.0-flash

    ges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     is
    -0.51
    Values
    -0.46
    add
    -0.43
    is
    -0.42
    User
    -0.41
    _
    -0.39
     aufgebaut
    -0.39
     values
    -0.38
    Before
    -0.38
    ISupport
    -0.38
    POSITIVE LOGITS
    tvguidetime
    0.96
     MainAxisSize
    0.94
    CppMethod
    0.88
    ioutil
    0.88
    脚注の使い方
    0.88
     виправивши
    0.86
    esModule
    0.84
    PhysRevD
    0.84
     MonoBehaviour
    0.82
     useRouter
    0.82
    Activations Density 1.030%

    No Known Activations