INDEX

Explanations

words and phrases related to medical conditions and contrasting opinions

oai_token-act-pair · gemini-2.0-flash

medical conditions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 CURIAM

-0.63

 كومونز

-0.60

endforeach

-0.56

LETIN

-0.52

hearsed

-0.51

spira

-0.50

TacToe

-0.49

cerely

-0.48

enumii

-0.47

 tanda

-0.46

POSITIVE LOGITS

 صوتيه

0.69

ConstraintMaker

0.66

MigrationBuilder

0.61

 counterpart

0.60

 Diſ

0.60

 فريبيس

0.59

 ſmall

0.58

 Administrativna

0.57

 autocollant

0.56

Sucesor

0.56

Activations Density 2.769%

words and phrases related to medical conditions and contrasting opinions

medical conditions

No Comments

No Known Activations