INDEX

Explanations

words related to scientific topics, especially medical and biological concepts

oai_token-act-pair · gemini-2.0-flash

bodily processes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

rungsseite

-0.66

henswürdigkeiten

-0.61

存于互联网档案馆

-0.61

 فريبيس

-0.59

HostException

-0.55

 resourceCulture

-0.54

locene

-0.54

ymce

-0.51

martre

-0.51

POSITIVE LOGITS

 home

0.56

Espèce

0.53

home

0.48

 bodily

0.47

 Home

0.45

Manbalar

0.44

Mol

0.42

bio

0.42

\{\\

0.42

chemical

0.41

Activations Density 3.058%

words related to scientific topics, especially medical and biological concepts

bodily processes

No Comments

No Known Activations