INDEX

Explanations

medical and scientific terminology, often related to biological processes and research

oai_token-act-pair · gemini-2.0-flash

vitro

np_max-act · gemini-2.0-flash

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.50

 bosons

-0.49

遺伝

-0.45

ocardium

-0.45

gesterone

-0.44

-0.43

酶

-0.43

 zebrafish

-0.43

 ELISA

-0.42

-0.39

POSITIVE LOGITS

Geplaatst

1.17

 ostavi

1.04

contentLoaded

0.98

Autoritní

0.97

 nahilalakip

0.95

исленность

0.94

########.

0.93

 OMIT

0.88

__":

0.86

 pinulongan

0.85

Activations Density 3.012%

medical and scientific terminology, often related to biological processes and research

vitro

No Comments

No Known Activations