INDEX

Explanations

mentions of liking something or being interested in something

oai_token-act-pair · gemini-2.0-flash

positive sentiment

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

UrlResolution

-0.67

HomeAsUpEnabled

-0.63

曖昧さ回避

-0.51

#+#

-0.51

 يتيمه

-0.51

RenderAtEndOf

-0.49

 snippetHide

-0.48

 beginnetje

-0.45

oneofs

-0.45

 Réponses

-0.44

POSITIVE LOGITS

RunAsync

0.57

to

0.57

 να

0.56

 libri

0.54

 chlorine

0.53

ofern

0.53

 circon

0.53

å

0.52

ειν

0.52

ρίζ

0.52

Activations Density 2.697%

mentions of liking something or being interested in something

positive sentiment

No Comments

No Known Activations