INDEX

Explanations

positive and negative sentiment

oai_token-act-pair · gemini-2.0-flash

positive or negative

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

ftagPool

-0.81

 Paglinawan

-0.80

 المعيارى

-0.79

 myſelf

-0.73

 itſelf

-0.70

RenderAtEndOf

-0.69

 jspb

-0.68

 becauſe

-0.67

ſelf

-0.66

 poffible

-0.66

POSITIVE LOGITS

peg

0.49

UserScript

0.48

0.47

sidemargin

0.45

 keting

0.45

IntoConstraints

0.44

isela

0.44

 Chevron

0.44

är

0.43

Activations Density 4.140%

positive and negative sentiment

positive or negative

No Comments

No Known Activations