INDEX

Explanations

text that discusses dividing things into groups

oai_token-act-pair · gemini-2.0-flash

Numbers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.27

 myſelf

-1.26

Efq

-1.18

 Monfieur

-1.18

 themſelves

-1.16

 himſelf

-1.13

 houſe

-1.12

 Theſe

-1.10

 Reſ

-1.09

 raiſ

-1.06

POSITIVE LOGITS

 general

0.66

sub

0.53

general

0.52

0.50

 General

0.46

 broad

0.46

General

0.45

sub

0.45

Activations Density 4.084%

text that discusses dividing things into groups

Numbers

No Comments

No Known Activations