INDEX

Explanations

journal references

oai_token-act-pair · gemini-2.0-flash

journal articles

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

Negative Logits

contentLoaded

-0.79

complexType

-0.71

'},

-0.63

 IBRARY

-0.63

 ExecuteAsync

-0.62

berdayakan

-0.62

NUMX

-0.61

esterday

-0.61

 disponibilités

-0.60

 Penh

-0.60

POSITIVE LOGITS

LE

0.56

kloped

0.49

de

0.49

le

0.48

 strani

0.47

SH

0.46

0.45

springframework

0.45

Gar

0.44

ще

0.44

Activations Density 0.887%

journal references

journal articles

No Known Activations