INDEX

Explanations

SQL code snippets

oai_token-act-pair · gemini-2.0-flash

database queries

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

kloped

-0.68

fromnode

-0.67

 noDo

-0.59

awtextra

-0.59

 ChromeDriver

-0.58

Ƚ

-0.57

rąg

-0.57

 jadi

-0.57

المشاركات

-0.54

 CreateTagHelper

-0.54

POSITIVE LOGITS

 estekak

0.62

 cheeks

0.51

+:+

0.48

ácii

0.48

PDR

0.47

ControllerAdvice

0.45

DPP

0.45

tison

0.45

ruption

0.45

 propOrder

0.45

Activations Density 9.156%

SQL code snippets

database queries

No Comments

No Known Activations