INDEX

Explanations

table and figure references, primers, probes, sequences and other terms common in scientific publications describing experimental procedures

oai_token-act-pair · gemini-2.0-flash

tables and lists

np_token-act-pair-logits · gemini-2.0-flash

lists

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

HasBeenSet

-0.75

localctx

-0.60

shadowRadius

-0.56

+:+

-0.55

例句

-0.55

Naissance

-0.51

RESUMO

-0.48

 cientí

-0.48

gink

-0.47

PyExc

-0.47

POSITIVE LOGITS

 lists

0.87

 list

0.75

 Lists

0.75

Lists

0.68

 detailed

0.68

see

0.67

DetailView

0.66

 listings

0.65

名单

0.65

 listed

0.65

Activations Density 2.544%

table and figure references, primers, probes, sequences and other terms common in scientific publications describing experimental procedures

tables and lists

lists

No Comments

No Known Activations