INDEX

Explanations

descriptive words used in marketing of cars or beauty products

oai_token-act-pair · gemini-2.0-flash

abstract qualities

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

feels

-0.61

looks

-0.56

Feels

-0.54

tvguidetime

-0.54

 feels

-0.52

 looks

-0.50

Looks

-0.48

 Looks

-0.47

 LOOKS

-0.47

stücke

-0.45

POSITIVE LOGITS

GEBURTSDATUM

0.90

CppMethod

0.73

 Мексичка

0.71

PageRoute

0.70

iconductor

0.69

'{@

0.69

ExtendWith

0.65

 насељу

0.65

LEncoder

0.64

 linkovi

0.63

Activations Density 6.384%

descriptive words used in marketing of cars or beauty products

abstract qualities

No Comments

No Known Activations