INDEX

Explanations

code with method signatures and parameter declarations

oai_token-act-pair · gemini-2.0-flash

param

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

param

-1.98

 param

-1.48

 PARAM

-1.32

Param

-1.27

 Param

-1.19

PARAM

-1.14

 Monfieur

-0.92

 parameter

-0.87

 Parameter

-0.86

 Params

-0.85

POSITIVE LOGITS

setVerticalGroup

0.64

mazoo

0.43

Obrázky

0.43

 bạc

0.42

SequentialGroup

0.42

Platinum

0.42

cum

0.41

Stacks

0.40

vision

0.40

 Bankruptcy

0.39

Activations Density 0.559%

code with method signatures and parameter declarations

param

No Comments

No Known Activations