INDEX

Explanations

words related to medical procedures and devices, especially those involving scopes

oai_token-act-pair · gemini-2.0-flash

cope

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 defaultstate

-0.85

 CreateTagHelper

-0.78

 незавершена

-0.73

حياته

-0.69

WebServlet

-0.69

rungsseite

-0.68

حياتها

-0.68

matchCondition

-0.68

 تضيفلها

-0.66

 jLabel

-0.62

POSITIVE LOGITS

 SqlCommand

0.50

agissait

0.49

 "..\..\..\

0.49

 Præ

0.46

iteness

0.45

 purpoſe

0.45

varlak

0.44

 definizione

0.44

 windy

0.44

stanbul

0.42

Activations Density 1.002%

words related to medical procedures and devices, especially those involving scopes

cope

No Comments

No Known Activations