INDEX

Explanations

code snippets, technical documentation, and programming-related expressions.

oai_token-act-pair · gemini-2.0-flash

code and lists

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 незавершена

-0.93

Personendaten

-0.70

PerformLayout

-0.68

хьтан

-0.67

 صوتيه

-0.64

istoitu

-0.63

 otomatig

-0.62

 himſelf

-0.62

Efq

-0.61

addCriterion

-0.61

POSITIVE LOGITS

nosaurus

0.56

Demografia

0.47

 date

0.47

alini

0.46

 posti

0.45

 anniversary

0.43

nage

0.43

мула

0.43

 list

0.42

versy

0.42

Activations Density 4.834%

code snippets, technical documentation, and programming-related expressions.

code and lists

No Comments

No Known Activations