INDEX

Explanations

snippets of code

oai_token-act-pair · gemini-2.0-flash

da

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Da

-1.45

Da

-1.37

da

-1.34

da

-1.23

DA

-0.99

DA

-0.98

Dan

-0.81

Да

-0.77

 Да

-0.75

Dan

-0.73

POSITIVE LOGITS

 disambiguazione

0.68

0.61

addGap

0.59

Приятного

0.55

 themſelves

0.54

ślę

0.54

numerusform

0.54

 reaſon

0.52

PMailer

0.52

engesch

0.51

Activations Density 10.277%

snippets of code

da

No Comments

No Known Activations