INDEX

Explanations

code snippets, references to code, and related terms

oai_token-act-pair · gemini-2.0-flash

Code/technical documentation

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

Negative Logits

思う

-0.51

стя

-0.46

articolo

-0.44

app

-0.42

but

-0.41

 toast

-0.40

 both

-0.40

env

-0.40

 öğ

-0.39

POSITIVE LOGITS

 initComponents

0.94

FormTagHelper

0.93

PerformLayout

0.93

MLLoader

0.90

SharedCtor

0.88

ArgsConstructor

0.88

 GenerationType

0.88

EDEFAULT

0.88

]")]

0.87

Hentet

0.87

Activations Density 1.266%

code snippets, references to code, and related terms

Code/technical documentation

No Known Activations