INDEX

Explanations

words associated with medical trials and analysis

oai_token-act-pair · gemini-2.0-flash

comparing measurements

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 myſelf

-0.69

 TType

-0.64

 ſeveral

-0.63

fromnode

-0.63

 itſelf

-0.63

 houſe

-0.61

 لينك

-0.60

Mutagenicity

-0.60

 fhort

-0.60

Efq

-0.59

POSITIVE LOGITS

pre

0.69

 חיצוניים

0.69

évaluateur

0.67

pre

0.62

principalColumn

0.61

 StringTokenizer

0.59

Pre

0.57

 שוליים

0.56

 pré

0.55

Pre

0.55

Activations Density 20.515%

words associated with medical trials and analysis

comparing measurements

No Comments

No Known Activations