INDEX

Explanations

the word "since" followed by a time reference

oai_token-act-pair · gemini-2.0-flash

since

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

 fince

-0.68

 since

-0.66

ніципа

-0.66

Tikang

-0.66

 SINCE

-0.65

 Himo

-0.65

ніципалі

-0.63

 سكانية

-0.62

tanooga

-0.61

 Showers

-0.61

POSITIVE LOGITS

enterOuterAlt

0.53

PrimaryKey

0.48

WebControls

0.47

PositiveButton

0.46

akteur

0.46

 propOrder

0.45

httphttps

0.44

CastException

0.42

Jegyzetek

0.42

AutoSize

0.42

Activations Density 0.469%

the word "since" followed by a time reference

since

No Comments

No Known Activations