INDEX

Explanations

references to spans of time, particularly weeks and years

oai_token-act-pair · gemini-2.0-flash

Time periods and events

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 last

-1.04

 propOrder

-0.96

今年は

-0.91

去年

-0.86

今年

-0.86

 letzten

-0.85

 fjor

-0.85

last

-0.84

今年も

-0.82

 année

-0.82

POSITIVE LOGITS

例句

0.44

HandleFunc

0.42

 Michoacán

0.41

 انداز

0.41

violi

0.40

ö

0.40

Communist

0.39

 Cantonese

0.38

beelding

0.38

Activations Density 1.048%

references to spans of time, particularly weeks and years

Time periods and events

No Comments

No Known Activations